Arrow Research search

Author name cluster

Mohit Bansal

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

85 papers
2 author rows

Possible papers

85

AAAI Conference 2026 Conference Paper

DreamRunner: Fine-Grained Compositional Story-to-Video Generation with Retrieval-Augmented Motion Adaptation

  • Zun Wang
  • Jialu Li
  • Han Lin
  • Jaehong Yoon
  • Mohit Bansal

Storytelling video generation (SVG) aims to produce coherent and visually rich multi-scene videos that follow a structured narrative. Existing methods primarily employ LLM for high-level planning to decompose a story into scene-level descriptions, which are then independently generated and stitched together. However, these approaches struggle with generating high-quality videos aligned with the complex single-scene description, as visualizing such complex description involves coherent composition of multiple objects/events, complex motion synthesis and character customization with sequential motions. To address these challenges, we propose DREAMRUNNER, a novel story-to-video generation method: First, we structure the input script using a large language model (LLM) to facilitate both coarse-grained scene planning as well as fine-grained object-level layout planning. Next, DREAMRUNNER presents retrieval-augmented test-time adaptation to capture target motion priors for objects in each scene, supporting diverse motion customization based on retrieved videos, thus facilitating the generation of new videos with complex, scripted motions. Lastly, we propose a novel spatial-temporal region-based 3D attention and prior injection module SR3AI for fine-grained object-motion binding and frame-by-frame spatial-temporal semantic control. We compare DREAMRUNNER with various SVG baselines, demonstrating state-of-the-art performance in character consistency, text alignment, and smooth transitions. Additionally, DREAMRUNNER exhibits strong fine-grained condition-following ability in compositional text-to-video generation, significantly outperforming baselines on T2V-ComBench. Finally, we demonstrate DREAMRUNNER’s ability to generate multi-character interactions with qualitative examples.

PDF Details DOI

TMLR Journal 2026 Journal Article

SiLVR: A Simple Language-based Video Reasoning Framework

  • Ce Zhang
  • Yan-Bo Lin
  • Ziyang Wang
  • Mohit Bansal
  • Gedas Bertasius

Recent advances in test-time optimization have led to remarkable reasoning capabilities in Large Language Models (LLMs), enabling them to solve highly complex problems in math and coding. However, the reasoning capabilities of multimodal LLMs (MLLMs) still significantly lag, especially for complex video-language tasks. To address this issue, we present SILVR, a Simple Language-based Video Reasoning framework that decomposes complex video understanding into two stages. In the first stage, SILVR transforms raw video into language-based representations using multisensory inputs, such as short clip captions and audio/speech subtitles. In the second stage, language descriptions are fed into a powerful reasoning LLM to solve complex video-language understanding tasks. To handle long-context multisensory inputs, we use an Adaptive Context Reduction scheme, which dynamically determines the temporal granularity with which to sample the tokens. Our simple, modular, and training-free video reasoning framework achieves the best-reported results on Video-MME (long), Video-MMMU (comprehension), Video-MMLU, CGBench, and EgoLife. Furthermore, our empirical study focused on video reasoning capabilities shows that, despite not being explicitly trained on video, strong reasoning LLMs can effectively aggregate multisensory input information from video, speech, and audio for complex temporal, causal, long-context, and knowledge acquisition reasoning tasks in video. More details can be found at https://sites.google.com/cs.unc.edu/silvr.

PDF Details

NeurIPS Conference 2025 Conference Paper

4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time

  • Ziqiao Ma
  • Xuweiyi Chen
  • Shoubin Yu
  • Sai Bi
  • Kai Zhang
  • Ziwen Chen
  • Sihan Xu
  • Jianing Yang

Can we scale 4D pretraining to learn general space-time representations that reconstruct an object from a few views at some times to any view at any time? We provide an affirmative answer with 4D-LRM, the first large-scale 4D reconstruction model that takes input from unconstrained views and timestamps and renders arbitrary novel view-time combinations. Unlike prior 4D approaches, e. g. , optimization-based, geometry-based, or generative, that struggle with efficiency, generalization, or faithfulness, 4D-LRM learns a unified space-time representation and directly predicts per-pixel 4D Gaussian primitives from posed image tokens across time, enabling fast, high-quality rendering at, in principle, infinite frame rate. Our results demonstrate that scaling spatiotemporal pretraining enables accurate and efficient 4D reconstruction. We show that 4D-LRM generalizes to novel objects, interpolates across time, and handles diverse camera setups. It reconstructs 24-frame sequences in one forward pass with less than 1. 5 seconds on a single A100 GPU.

PDF Details

TMLR Journal 2025 Journal Article

A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning

  • Prateek Yadav
  • Colin Raffel
  • Mohammed Muqeeth
  • Lucas Caccia
  • Haokun Liu
  • Tianlong Chen
  • Mohit Bansal
  • Leshem Choshen

The availability of performant pre-trained models has led to a proliferation of fine-tuned expert models that are specialized to a particular domain or task. Model MoErging methods aim to recycle expert models to create an aggregate system with improved performance or generalization. A key component of MoErging methods is the creation of a router that decides which expert model(s) to use for a particular input or application. The promise, effectiveness, and large design space of MoErging has spurred the development of many new methods over the past few years. This rapid pace of development has made it challenging to compare different MoErging methods, which are rarely compared to one another and are often validated in different experimental setups. To remedy such gaps, we present a comprehensive survey of MoErging methods that includes a novel taxonomy for cataloging key design choices and clarifying suitable applications for each method. Apart from surveying MoErging research, we inventory software tools and applications that make use of MoErging. We additionally discuss related fields of study such as model merging, multitask learning, and mixture-of-experts models. Taken as a whole, our survey provides a unified overview of existing MoErging methods and creates a solid foundation for future work in this burgeoning field.

PDF Details

ICLR Conference 2025 Conference Paper

Adapt-∞: Scalable Continual Multimodal Instruction Tuning via Dynamic Data Selection

  • Adyasha Maharana
  • Jaehong Yoon
  • Tianlong Chen 0001
  • Mohit Bansal

Visual instruction datasets from various distributors are released at different times and often contain a significant number of semantically redundant text-image pairs, depending on their task compositions (i.e., skills) or reference sources. This redundancy greatly limits the efficient deployment of continually adaptable multimodal large language models, hindering their ability to refine existing skills and acquire new competencies over time. To address this, we reframe the problem of lifelong Instruction Tuning (LiIT) via data selection, where the model automatically selects beneficial samples to learn from earlier and new datasets based on the current state of acquired knowledge in the model. Based on empirical analyses that show that selecting the best data subset using a static importance measure is often ineffective for multi-task datasets with evolving distributions, we propose Adapt-$\infty$, a new multi-way and adaptive data selection approach that dynamically balances sample efficiency and effectiveness during LiIT. We first construct pseudo-skill clusters by grouping gradient-based sample vectors. Next, we select the best-performing data selector for each skill cluster from a pool of selector experts, including our newly proposed scoring function, Image Grounding score. This data selector samples a subset of the most important samples from each skill cluster for training. To prevent the continuous increase in the size of the dataset pool during LIT, which would result in excessive computation, we further introduce a cluster-wise permanent data pruning strategy to remove the most semantically redundant samples from each cluster, keeping computational requirements manageable. We validate the effectiveness and efficiency of Adapt-$\infty$ over a sequence of various multimodal instruction tuning datasets with various tasks, including (Knowledge) VQA, multilingual, grounding, reasoning, language-only, and multi-image comprehension tasks. Training with samples selected by Adapt-$\infty$ alleviates catastrophic forgetting, especially for rare tasks, and promotes forward transfer across the continuum using only a fraction of the original datasets.

Details

ICLR Conference 2025 Conference Paper

Anyprefer: An Agentic Framework for Preference Data Synthesis

  • Yiyang Zhou
  • Zhaoyang Wang 0004
  • Tianle Wang 0009
  • Shangyu Xing
  • Peng Xia 0005
  • Bo Li 0026
  • Kaiyuan Zheng
  • Zijian Zhang 0010

High-quality preference data is essential for aligning foundation models with human values through preference learning. However, manual annotation of such data is often time-consuming and costly. Recent methods often adopt a self-rewarding approach, where the target model generates and annotates its own preference data, but this can lead to inaccuracies since the reward model shares weights with the target model, thereby amplifying inherent biases. To address these issues, we propose Anyprefer, a framework designed to synthesize high-quality preference data for aligning the target model. Anyprefer frames the data synthesis process as a cooperative two-player Markov Game, where the target model and the judge model collaborate together. Here, a series of external tools are introduced to assist the judge model in accurately rewarding the target model’s responses, mitigating biases in the rewarding process. In addition, a feedback mechanism is introduced to optimize prompts for both models, enhancing collaboration and improving data quality. The synthesized data is compiled into a new preference dataset, Anyprefer-V1, consisting of 58K high-quality preference pairs. Extensive experiments show that Anyprefer significantly improves model alignment performance across four main applications, covering 21 datasets, achieving average improvements of 18.55% in five natural language generation datasets, 3.66% in nine vision-language understanding datasets, 30.05% in three medical image analysis datasets, and 16.00% in four visuo-motor control tasks.

Details

NeurIPS Conference 2025 Conference Paper

Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents

  • Han Lin
  • Jaemin Cho
  • Amir Zadeh
  • Chuan Li
  • Mohit Bansal

There is growing interest in integrating high-fidelity visual synthesis capabilities into large language models (LLMs) without compromising their strong reasoning capabilities. Existing methods that directly train LLMs or bridge LLMs and diffusion models usually suffer from costly training since the backbone LLMs have not seen image representations during pretraining. We present Bifrost-1, a unified framework that bridges pretrained multimodal LLMs (MLLMs) and diffusion models using patch-level CLIP image embeddings as latent variables, which are natively aligned with the MLLM's CLIP visual encoder. These patch-level image embeddings are integrated into the diffusion model with a lightweight adaptation of its ControlNet. To retain the original multimodal reasoning capabilities of MLLMs, we equip the MLLM with a visual generation branch initialized from the original MLLM parameters when predicting the patch-level image embeddings. By seamlessly integrating pretrained MLLMs and diffusion models with patch-level CLIP latents, our framework enables high-fidelity controllable image generation with significant training efficiency. Our experiments demonstrate that Bifrost-1 achieves comparable or better performance than previous methods in terms of visual fidelity and multimodal understanding, with substantially lower compute during training. We also provide comprehensive ablation studies showing the effectiveness of our design choices. Project page: https: //bifrost-1. github. io.

PDF Details

ICLR Conference 2025 Conference Paper

Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel

  • Zun Wang 0001
  • Jialu Li 0001
  • Yicong Hong
  • Songze Li
  • Kunchang Li 0002
  • Shoubin Yu
  • Yi Wang 0074
  • Yu Qiao 0001

Creating high-quality data for training robust language-instructed agents is a long-lasting challenge in embodied AI. In this paper, we introduce a Self-Refining Data Flywheel (SRDF) that generates high-quality and large-scale navigational instruction-trajectory pairs by iteratively refining the data pool through the collaboration between two models, the instruction generator and the navigator, without any human-in-the-loop annotation. Specifically, SRDF starts with using a base generator to create an initial data pool for training a base navigator, followed by applying the trained navigator to filter the data pool. This leads to higher-fidelity data to train a better generator, which can, in turn, produce higher-quality data for training the next-round navigator. Such a flywheel establishes a data self-refining process, yielding a continuously improved and highly effective dataset for large-scale language-guided navigation learning. Our experiments demonstrate that after several flywheel rounds, the navigator elevates the performance boundary from 70\% to 78\% SPL on the classic R2R test set, surpassing human performance (76\%) for the first time. Meanwhile, this process results in a superior generator, evidenced by a SPICE increase from 23.5 to 26.2, better than all previous VLN instruction generation methods. Finally, we demonstrate the scalability of our method through increasing environment and instruction diversity, and the generalization ability of our pre-trained navigator across various downstream navigation tasks, surpassing state-of-the-art methods by a large margin in all cases.

Details

TMLR Journal 2025 Journal Article

ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and Quantization

  • Prateek Yadav
  • Leshem Choshen
  • Colin Raffel
  • Mohit Bansal

Parameter-efficient fine-tuning (PEFT) enables creation of specialized language models for diverse tasks, resulting in numerous expert modules. In many practical use cases, these expert PEFT modules are integrated into a single model that answers arbitrary queries by routing queries to different experts. However, only a few experts can be kept in GPU memory due to memory constraints. Consequently, expert modules are frequently loaded and offloaded between CPU/GPU memory or disk storage. This frequent swapping dramatically increases communication overhead, leading unacceptable latency and degrading user experience. The large size of modern PEFT modules further exacerbates this latency. For example, QLoRA experts for 65B LLaMA are 3.2GB, making swapping a major communication bottleneck, particularly in memory-constrained environments. To address these issues, we present ComPEFT (compressed PEFT), a novel method for compressing fine-tuning residuals (task vectors) of PEFT models. Reducing expert PEFT module size effectively addresses both memory and communication limitations, facilitating faster swapping and enabling a higher density of experts within a given memory footprint. ComPEFT employs sparsification and ternary quantization to reduce PEFT module size without any additional training while preserving or enhancing model performance. Extensive evaluation across T5, T0, and LLaMA-based models with 200M − 65B parameters, ComPEFT achieves compression ratios of 8x − 50x. Specifically, we show that ComPEFT improves with scale – stronger models exhibit higher compressibility and better performance. We show ComPEFT applied to LLaMA − 65B outperforms QLoRA by 4.16% on MMLU with a 26x storage size reduction. Additionally, compressed experts produced by ComPEFT maintain few-shot compositional generalization capabilities, facilitate efficient communication and computation, and exhibit enhanced performance when merged. Lastly, we provide an analysis of different method components, compare ComPEFT with other PEFT methods, and test its efficacy for compressing full finetuning residual.

PDF Details

ICLR Conference 2025 Conference Paper

CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion

  • Shoubin Yu
  • Jaehong Yoon
  • Mohit Bansal

Despite impressive advancements in recent multimodal reasoning approaches, they are still limited in flexibility and efficiency, as these models typically process only a few fixed modality inputs and require updates to numerous parameters. This paper tackles these critical challenges and proposes CREMA, a generalizable, highly efficient, and modular modality-fusion framework that can incorporate many new modalities to enhance video reasoning. We first augment multiple informative modalities (such as optical flow, 3D point cloud, audio, thermal heatmap, and touch map) from given videos without extra human annotation by leveraging sensors or existing pre-trained models. Next, we introduce a query transformer with multiple parameter-efficient modules associated with each accessible modality. It projects diverse modality features to the LLM token embedding space, allowing the model to integrate different data types for response generation. Furthermore, we propose a novel progressive multimodal fusion design supported by a lightweight fusion module and modality-sequential training strategy. It helps compress information across various assisting modalities, maintaining computational efficiency in the LLM while improving performance. We validate our method on seven video-language reasoning tasks assisted by diverse modalities, including conventional VideoQA and Video-Audio/3D/Touch/Thermal QA, and achieve better/equivalent performance against strong multimodal LLMs, including OneLLM, BLIP-2, and SeViLA while reducing over 90% trainable parameters. We provide extensive analyses of CREMA, including the impact of each modality on reasoning domains, the design of the fusion module, and example visualizations.

Details

ICLR Conference 2025 Conference Paper

Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model

  • Han Lin
  • Jaemin Cho 0001
  • Abhay Zala
  • Mohit Bansal

ControlNets are widely used for adding spatial control to text-to-image diffusion models. However, when it comes to controllable video generation, ControlNets cannot be directly integrated into new backbones due to feature space mismatches, and training ControlNets for new backbones can be a significant burden for many users. Furthermore, applying ControlNets independently to different frames can not effectively maintain object temporal consistency. To address these challenges, we introduce Ctrl-Adapter, an efficient and versatile framework that adds diverse controls to any image/video diffusion models through the adaptation of pretrained ControlNets. Ctrl-Adapter offers strong and diverse capabilities, including image and video control, sparse-frame video control, fine-grained patch-level multi-condition control, zero-shot adaptation to unseen conditions, and supports a variety of downstream tasks beyond spatial control, including video editing, video style transfer, and text-guided motion control. With six diverse U-Net/DiT-based image/video diffusion models (SDXL, PixArt-α, I2VGen-XL, SVD, Latte, Hotshot-XL), Ctrl-Adapter matches the performance of pretrained ControlNets on COCO and achieves the state-of-the-art on DAVIS 2017 with significantly lower computation (< 10 GPU hours).

Details

ICLR Conference 2025 Conference Paper

DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedback

  • Zaid Khan 0001
  • Elias Stengel-Eskin
  • Jaemin Cho 0001
  • Mohit Bansal

The process of creating training data to teach models is currently driven by humans, who manually analyze model weaknesses and plan how to create data that improves a student model. Recent approaches using large language models (LLMs) as annotators reduce human annotation effort, but still require humans to interpret feedback from evaluations and control the LLM to produce data the student needs. Automating this labor-intensive process by creating autonomous data generation agents – or teachers – is desirable, but requires environments that can simulate the feedback-driven, iterative, closed loop of data creation. To enable rapid and scalable testing for such agents and their modules, we introduce DataEnvGym, a testbed of teacher environments for data generation agents. DataEnvGym frames data generation as a sequential decision-making task, involving an agent consisting of a data generation policy (which generates a plan for creating training data) and a data generation engine (which transforms the plan into data), inside an environment that provides feedback from a student. The agent’s end goal is to improve student model performance. Students are iteratively trained and evaluated on generated data, with their feedback (in the form of errors or weak skills) being reported to the agent after each iteration. As a general-purpose testbed, DataEnvGym includes multiple instantiations of teacher environments across three levels of structure in the state representation and action space, with varying levels of scaffolding support. More structured environments are based on automatically-inferred skills and offer a higher degree of interpretability and control over the curriculum. We support developing and testing data generation agents in four diverse tasks covering text, images, and actions (mathematics, programming, visual question answering, and tool-use) and test multiple student and teacher models. We find that example agents in our teaching environments can iteratively improve students across diverse tasks and settings. Moreover, we show that environments can teach different skill levels and can be used to test variants of key modules, pointing to directions of future work in improving data generation agents, engines, and feedback mechanisms. Project page: https://DataEnvGym.github.io.

Details

NeurIPS Conference 2025 Conference Paper

LASeR: Learning to Adaptively Select Reward Models with Multi-Arm Bandits

  • Duy Nguyen
  • Archiki Prasad
  • Elias Stengel-Eskin
  • Mohit Bansal

Reward Models (RMs) are crucial to aligning large language models (LLMs), but the degree to which an RM specialized to one task (e. g. writing) generalizes to new tasks (e. g. math) is often not known a priori, often making using only one fixed RM to train LLMs suboptimal. However, optimizing LLMs with multiple RMs simultaneously can incur a prohibitively high computational cost and lead to conflicting signals from different RMs that may degrade performance. To address these challenges, we introduce LASeR (Learning to Adaptively Select Rewards), which frames reward model selection as a multi-armed bandit problem, iteratively and efficiently training LLMs using multiple RMs by selecting the most well-suited RM for each instance. On commonsense and math reasoning tasks, we show that LASeR boosts iterative LLM training, improving the absolute average accuracy of Llama-3-8B over three datasets by $2. 67$% over an ensemble of RM scores while also showing superior efficiency (e. g. , a $2\times$ speedup). Moreover, on WildChat (open-ended instruction-following tasks), LASeR leads to a $72. 69$% AlpacaEval win rate over the RM score ensemble baseline. Extending to long-context generation, LASeR improves by $2. 96$ F1 points (avg. ) on single-document QA tasks and $2. 97$ F1 points on few-shot learning over the RM score ensemble baseline with best-of-$n$ sampling. We include our code in the supplementary.

PDF Details

NeurIPS Conference 2025 Conference Paper

ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding

  • Yiyang Zhou
  • Yangfan He
  • Yaofeng Su
  • Siwei Han
  • Joel Jang
  • Gedas Bertasius
  • Mohit Bansal
  • Huaxiu Yao

Video understanding is fundamental to tasks such as action recognition, video reasoning, and robotic control. Early video understanding methods based on large vision-language models (LVLMs) typically adopt a single-pass reasoning paradigm without dynamic feedback, limiting the model’s capacity to self-correct and adapt in complex scenarios. Recent efforts have attempted to address this limitation by incorporating reward models and reinforcement learning to enhance reasoning, or by employing tool-agent frameworks. However, these approaches face several challenges, including high annotation costs, reward signals that fail to capture real-time reasoning states, and low inference efficiency. To overcome these issues, we propose ReAgent-V, a novel agentic video understanding framework that integrates efficient frame selection with real-time reward generation during inference. These reward signals not only guide iterative answer refinement through a multi-perspective reflection mechanism—adjusting predictions from conservative, neutral, and aggressive viewpoints—but also enable automatic filtering of high-quality data for supervised fine-tuning (SFT), direct preference optimization (DPO), and group relative policy optimization (GRPO). ReAgent-V is lightweight, modular, and extensible, supporting flexible tool integration tailored to diverse tasks. Extensive experiments on 12 datasets across three core applications—video understanding, video reasoning enhancement, and vision-language-action model alignment—demonstrate significant gains in generalization and reasoning, with improvements of up to 6. 9%, 2. 1%, and 9. 8%, respectively, highlighting the effectiveness and versatility of the proposed framework.

PDF Details

TMLR Journal 2025 Journal Article

Reliable and Responsible Foundation Models

  • Xinyu Yang
  • Junlin Han
  • Rishi Bommasani
  • Jinqi Luo
  • Wenjie Qu
  • Wangchunshu Zhou
  • Adel Bibi
  • Xiyao Wang

Foundation models, including Large Language Models (LLMs), Multimodal Large Language Models (MLLMs), Image Generative Models (i.e, Text-to-Image Models and Image-Editing Models), and Video Generative Models, have become essential tools with broad applications across various domains such as law, medicine, education, finance, and beyond. As these models see increasing real-world deployment, ensuring their reliability and responsibility has become critical for academia, industry, and government. This survey addresses the reliable and responsible development of foundation models. We explore critical issues, including bias and fairness, security and privacy, uncertainty, explainability, and distribution shift. Our research also covers model limitations, such as hallucinations, as well as methods like alignment and Artificial Intelligence-Generated Content (AIGC) detection. For each area, we review the current state of the field and outline concrete future research directions. Additionally, we discuss the intersections between these areas, highlighting their connections and shared challenges. We hope our survey fosters the development of foundation models that are not only powerful but also ethical, trustworthy, reliable, and socially responsible.

PDF Details

ICLR Conference 2025 Conference Paper

SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation

  • Jaehong Yoon
  • Shoubin Yu
  • Vaidehi Patil
  • Huaxiu Yao
  • Mohit Bansal

Recent advances in diffusion models have significantly enhanced their ability to generate high-quality images and videos, but they have also increased the risk of producing unsafe content. Existing unlearning/editing-based methods for safe generation remove harmful concepts from models but face several challenges: (1) They cannot instantly remove harmful or undesirable concepts (e.g., artist styles) without additional training. (2) Their safe generation capabilities depend on collected training data. (3) They alter model weights, risking degradation in quality for content unrelated to the targeted toxic concepts. To address these challenges, we propose SAFREE, a novel, training-free approach for safe text-to-image and video generation, that does not alter the model's weights. Specifically, we detect a subspace corresponding to a set of toxic concepts in the text embedding space and steer prompt token embeddings away from this subspace, thereby filtering out harmful content while preserving intended semantics. To balance the trade-off between filtering toxicity and preserving safe concepts, SAFREE incorporates a novel self-validating filtering mechanism that dynamically adjusts the denoising steps when applying the filtered embeddings. Additionally, we incorporate adaptive re-attention mechanisms within the diffusion latent space to selectively diminish the influence of features related to toxic concepts at the pixel level. By integrating filtering across both textual embedding and visual latent spaces, SAFREE ensures coherent safety checking, preserving the fidelity, quality, and safety of the generated outputs. Empirically, SAFREE achieves state-of-the-art performance in suppressing unsafe content in T2I generation (reducing it by 22% across 5 datasets) compared to other training-free methods and effectively filters targeted concepts, e.g., specific artist styles, while maintaining high-quality output. It also shows competitive results against training-based methods. We further extend SAFREE to various T2I backbones and T2V tasks, showcasing its flexibility and generalization. As generative AI rapidly evolves, SAFREE provides a robust and adaptable safeguard for ensuring safe visual generation.

Details

ICLR Conference 2025 Conference Paper

See It from My Perspective: How Language Affects Cultural Bias in Image Understanding

  • Amith Ananthram
  • Elias Stengel-Eskin
  • Mohit Bansal
  • Kathleen McKeown

Vision-language models (VLMs) can respond to queries about images in many languages. However, beyond language, culture affects how we see things. For example, individuals from Western cultures focus more on the central figure in an image while individuals from East Asian cultures attend more to scene context (Nisbett 2001). In this work, we characterize the Western bias of VLMs in image understanding and investigate the role that language plays in this disparity. We evaluate VLMs across subjective and objective visual tasks with culturally diverse images and annotations. We find that VLMs perform better on the Western split than on the East Asian split of each task. Through controlled experimentation, we trace one source of this bias in image understanding to the lack of diversity in language model construction. While inference in a language nearer to a culture can lead to reductions in bias, we show it is much more effective when that language was well-represented during text-only pre-training. Interestingly, this yields bias reductions even when prompting in English. Our work highlights the importance of richer representation of all languages in building equitable VLMs.

Details

ICML Conference 2025 Conference Paper

Self-Consistency Preference Optimization

  • Archiki Prasad
  • Weizhe Yuan
  • Richard Yuanzhe Pang
  • Jing Xu 0014
  • Maryam Fazel-Zarandi
  • Mohit Bansal
  • Sainbayar Sukhbaatar
  • Jason Weston

Self-alignment, whereby models learn to improve themselves without human annotation, is a rapidly growing research area. However, existing techniques often fail to improve complex reasoning tasks due to the difficulty of assigning correct rewards. An orthogonal approach that is known to improve correctness is self-consistency, a method applied at inference time based on multiple sampling in order to find the most consistent answer. In this work, we extend the self-consistency concept to help train models. We thus introduce self-consistency preference optimization (ScPO), which iteratively trains consistent answers to be preferred over inconsistent ones on unsupervised new problems. We show ScPO leads to large improvements over conventional reward model training on reasoning tasks such as GSM8K and MATH, closing the gap with supervised training with gold answers or preferences, and that combining ScPO with standard supervised learning improves results even further. On ZebraLogic, ScPO finetunes Llama-3 8B to be superior to Llama-3 70B, Gemma-2 27B, and Claude-3 Haiku.

Details

ICLR Conference 2025 Conference Paper

System 1. x: Learning to Balance Fast and Slow Planning with Language Models

  • Swarnadeep Saha
  • Archiki Prasad
  • Justin Chih-Yao Chen
  • Peter Hase
  • Elias Stengel-Eskin
  • Mohit Bansal

Language models can be used to solve long-horizon planning problems in two distinct modes. In a fast 'System-1' mode, models directly generate plans without any explicit search or backtracking, and in a slow 'System-2' mode, they plan step-by-step by explicitly searching over possible actions. System-2 planning, while typically more effective, is also computationally more expensive and often infeasible for long plans or large action spaces. Moreover, isolated System-1 or System-2 planning ignores the user's end goals and constraints (e.g., token budget), failing to provide ways for the user to control the model's behavior. To this end, we propose the System-1.x Planner, a framework for controllable planning with language models that is capable of generating hybrid plans and balancing between the two planning modes based on the difficulty of the problem at hand. System-1.x consists of (i) a controller, (ii) a System-1 Planner, and (iii) a System-2 Planner. Based on a user-specified hybridization factor x governing the degree to which the system uses System-1 vs. System-2, the controller decomposes a planning problem into subgoals, and classifies them as easy or hard to be solved by either System-1 or System-2, respectively. We fine-tune all three components on top of a single base LLM, requiring only search traces as supervision. Experiments with two diverse planning tasks -- Maze Navigation and Blocksworld -- show that our System-1.x Planner outperforms a System-1 Planner, a System-2 Planner trained to approximate A* search, and also a symbolic planner (A* search), given a state exploration budget. We also demonstrate the following key properties of our planner: (1) controllability: by adjusting the hybridization factor x (e.g., System-1.75 vs. System-1.5) we can perform more (or less) search, improving performance, (2) flexibility: by building a neuro-symbolic variant composed of a neural System-1 planner and a symbolic System-2 planner, we can take advantage of existing symbolic methods, and (3) generalizability: by learning from different search algorithms (BFS, DFS, A*), we show that our method is robust to the choice of search algorithm used for training.

Details

ICLR Conference 2025 Conference Paper

Unbounded: A Generative Infinite Game of Character Life Simulation

  • Jialu Li 0001
  • Yuanzhen Li
  • Neal Wadhwa
  • Yael Pritch
  • David E. Jacobs
  • Michael Rubinstein
  • Mohit Bansal
  • Nataniel Ruiz

We introduce the concept of a generative infinite game, a video game that transcends the traditional boundaries of finite, hard-coded systems by using generative models. Inspired by James P. Carse's distinction between finite and infinite games, we leverage recent advances in generative AI to create Unbounded: a game of character life simulation that is fully encapsulated in generative models. Specifically, Unbounded draws inspiration from sandbox life simulations and allows you to interact with your autonomous virtual character in a virtual world by feeding, playing with and guiding it - with open-ended mechanics generated by an LLM, some of which can be emergent. In order to develop Unbounded, we propose technical innovations in both the LLM and visual generation domains. Specifically, we present: (1) a specialized, distilled large language model (LLM) that dynamically generates game mechanics, narratives, and character interactions in real-time, and (2) a new dynamic regional image prompt Adapter (IP-Adapter) for vision models that ensures consistent yet flexible visual generation of a character across multiple environments. We evaluate our system through both qualitative and quantitative analysis, showing significant improvements in character life simulation, user instruction following, narrative coherence, and visual consistency for both characters and the environments compared to traditional related approaches.

Details

ICLR Conference 2025 Conference Paper

VEDIT: Latent Prediction Architecture For Procedural Video Representation Learning

  • Han Lin
  • Tushar Nagarajan
  • Nicolas Ballas
  • Mahmoud Assran
  • Mojtaba Komeili
  • Mohit Bansal
  • Koustuv Sinha

Procedural video representation learning is an active research area where the objective is to learn an agent which can anticipate and forecast the future given the present video input, typically in conjunction with textual annotations. Prior works often rely on large-scale pretraining of visual encoders and prediction models with language supervision. However, the necessity and effectiveness of extending compute intensive pretraining to learn video clip sequences with noisy text supervision have not yet been fully validated by previous works. In this work, we show that a strong off-the-shelf frozen pretrained visual encoder, along with a well designed prediction model, can achieve state-of-the-art (SoTA) performance in forecasting and procedural planning without the need for pretraining the prediction model, nor requiring additional supervision from language or ASR. Instead of learning representations from pixel space, our method utilizes the latent embedding space of publicly available vision encoders. By conditioning on frozen clip-level embeddings from observed steps to predict the actions of unseen steps, our prediction model is able to learn robust representations for forecasting through iterative denoising —leveraging the recent advances in diffusion transformers (Peebles & Xie, 2023). Empirical studies over a total of five procedural learning tasks across four datasets (NIV, CrossTask, COIN and Ego4D-v2) show that our model advances the strong baselines in long-horizon action anticipation (+2.6% in Verb ED@20, +3.1% in Noun ED@20), and significantly improves the SoTA in step forecasting (+5.0%), task classification (+3.8%), and procedure planning tasks (up to +2.28% in success rate, +3.39% in mAcc, and +0.90% in mIoU).

Details

TMLR Journal 2025 Journal Article

What Matters for Model Merging at Scale?

  • Prateek Yadav
  • Tu Vu
  • Jonathan Lai
  • Alexandra Chronopoulou
  • Manaal Faruqui
  • Mohit Bansal
  • Tsendsuren Munkhdalai

Model merging aims to combine multiple expert models into a more capable single model, offering benefits such as reduced storage and serving costs, improved generalization, and support for decentralized model development. Despite its promise, previous studies have primarily focused on merging a few small models. This leaves many unanswered questions about the effect of scaling model size and how it interplays with other key factors—like the base model quality and number of expert models— to affect the merged model’s performance. This work systematically evaluates the utility of model merging at scale for transformer based models to examine the impact of these different factors. We experiment with merging fully fine-tuned models using four popular merging methods—Averaging, Task Arithmetic, Dare-TIES, and TIES-Merging—across model sizes ranging from 1B to 64B parameters and merging up to 8 different expert models. We evaluate the merged models on both held-in tasks, i.e., the expert’s training tasks, and zero-shot generalization to unseen held-out tasks. Our wide range of experiments provide several new insights about merging transformer based language models at scale and the interplay between different factors. First, we find that merging is more effective when experts are created from strong base models, i.e., models with good zero-shot performance, compared to pre-trained ones. Second, larger models perform better when merged. Third merging consistently improves generalization capabilities. Notably, when merging eight large expert models, the merged models often generalize better compared to the multitask trained models. Fourth, we can better merge more expert models when working with larger models. Fifth, different merging methods behave very similarly at larger scales. Overall, our findings shed light on some interesting properties of model merging while also highlighting some limitations.

PDF Details

ICLR Conference 2024 Conference Paper

Analyzing and Mitigating Object Hallucination in Large Vision-Language Models

  • Yiyang Zhou
  • Chenhang Cui
  • Jaehong Yoon
  • Linjun Zhang
  • Zhun Deng
  • Chelsea Finn
  • Mohit Bansal
  • Huaxiu Yao

Large vision-language models (LVLMs) have shown remarkable abilities in understanding visual information with human languages. However, LVLMs still suffer from object hallucination, which is the problem of generating descriptions that include objects that do not actually exist in the images. This can negatively impact many vision-language tasks, such as visual summarization and reasoning. To address this issue, we propose a simple yet powerful algorithm, LVLM Hallucination Revisor (LURE), to post-hoc rectify object hallucination in LVLMs by reconstructing less hallucinatory descriptions. LURE is grounded in a rigorous statistical analysis of the key factors underlying object hallucination, including co-occurrence (the frequent appearance of certain objects alongside others in images), uncertainty (objects with higher uncertainty during LVLM decoding), and object position (hallucination often appears in the later part of the generated text). LURE can also be seamlessly integrated with any LVLMs. We evaluate LURE on six open-source LVLMs and found it outperforms the previous best approach in both general object hallucination evaluation metrics, GPT, and human evaluations.

Details

ICLR Conference 2024 Conference Paper

Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks

  • Vaidehi Patil
  • Peter Hase
  • Mohit Bansal

Pretrained language models sometimes possess knowledge that we do not wish them to, including memorized personal information and knowledge that could be used to harm people. They can also output toxic or harmful text. To mitigate these safety and informational issues, we propose an attack-and-defense framework for studying the task of deleting sensitive information directly from model weights. We study direct edits to model weights because (1) this approach should guarantee that particular deleted information is never extracted by future prompt attacks, and (2) it should protect against whitebox attacks, which is necessary for making claims about safety/privacy in a setting where publicly available model weights could be used to elicit sensitive information. Our threat model assumes that an attack succeeds if the answer to a sensitive question is located among a set of B generated candidates, based on scenarios where the information would be insecure if the answer is among B candidates. Experimentally, we show that even state-of-the-art model editing methods such as ROME struggle to truly delete factual information from models like GPT-J, as our whitebox and blackbox attacks can recover “deleted” information from an edited model 38% of the time. These attacks leverage two key observations: (1) that traces of deleted information can be found in intermediate model hidden states, and (2) that applying an editing method for one question may not delete information across rephrased versions of the question. Finally, we provide new defense methods that protect against some extraction attacks, but we do not find a single universally effective defense method. Our results suggest that truly deleting sensitive information is a tractable but difficult problem, since even relatively low attack success rates have potentially severe implications for the deployment of language models in a world where individuals enjoy ownership of their personal data, a right to privacy, and safety from harmful model outputs.

Details

ICLR Conference 2024 Conference Paper

D2 Pruning: Message Passing for Balancing Diversity & Difficulty in Data Pruning

  • Adyasha Maharana
  • Prateek Yadav
  • Mohit Bansal

In recent years, data quality has emerged as an important factor for training massive models. Analytical theories suggest that higher-quality data can lead to lower test errors in models trained on a fixed data budget. Moreover, a model can be trained on a lower compute budget without compromising performance if a dataset can be stripped of its redundancies. Coreset selection (or data pruning) seeks to select a subset of the training data so as to maximize the performance of models trained on this subset, also referred to as coreset. There are two dominant approaches: (1) geometry-based data selection for maximizing *data diversity* in the coreset, and (2) functions that assign *difficulty scores* to samples based on training dynamics. Optimizing for data diversity leads to a coreset that is biased towards easier samples, whereas, selection by difficulty ranking omits easy samples that are necessary for the training of deep learning models. This demonstrates that data diversity and importance scores are two complementary factors that need to be jointly considered during coreset selection. In this work, we represent a dataset as an undirected graph and propose a novel pruning algorithm, $\mathbb{D}^2$ Pruning, that uses message passing over this dataset graph for coreset selection. $\mathbb{D}^2$ Pruning updates the difficulty scores of each example by incorporating the difficulty of its neighboring examples in the dataset graph. Then, these updated difficulty scores direct a graph-based sampling method to select a coreset that encapsulates both diverse and difficult regions of the dataset space. We evaluate supervised and self-supervised versions of our method on various vision and NLP datasets. Results show that $\mathbb{D}^2$ Pruning improves coreset selection over previous state-of-the-art methods at low-to-medium pruning rates. Additionally, we find that using $\mathbb{D}^2$ Pruning for filtering large multimodal datasets leads to increased diversity in the dataset and improved generalization of pretrained models. Our work shows that $\mathbb{D}^2$ Pruning is a versatile framework for understanding and processing datasets.

Details

ICLR Conference 2024 Conference Paper

Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation

  • Jaemin Cho 0001
  • Yushi Hu
  • Jason M. Baldridge
  • Roopal Garg
  • Peter Anderson
  • Ranjay Krishna
  • Mohit Bansal
  • Jordi Pont-Tuset

Evaluating text-to-image models is notoriously difficult. A strong recent approach for assessing text-image faithfulness is based on QG/A (question generation and answering), which uses pre-trained foundational models to automatically generate a set of questions and answers from the prompt, and output images are scored based on whether these answers extracted with a visual question answering model are consistent with the prompt-based answers. This kind of evaluation is naturally dependent on the quality of the underlying QG and VQA models. We identify and address several reliability challenges in existing QG/A work: (a) QG questions should respect the prompt (avoiding hallucinations, duplications, and omissions) and (b) VQA answers should be consistent (not asserting that there is no motorcycle in an image while also claiming the motorcycle is blue). We address these issues with Davidsonian Scene Graph (DSG), an empirically grounded evaluation framework inspired by formal semantics, which is adaptable to any QG/A frameworks. DSG produces atomic and unique questions organized in dependency graphs, which (i) ensure appropriate semantic coverage and (ii) sidestep inconsistent answers. With extensive experimentation and human evaluation on a range of model configurations (LLM, VQA, and T2I), we empirically demonstrate that DSG addresses the challenges noted above. Finally, we present DSG-1k, an open-sourced evaluation benchmark that includes 1,060 prompts, covering a wide range of fine-grained semantic categories with a balanced distribution. We release the DSG-1k prompts and the corresponding DSG questions.

Details

ICLR Conference 2024 Conference Paper

ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models

  • Yi-Lin Sung
  • Jaehong Yoon
  • Mohit Bansal

Large Vision-Language Models (LVLMs) can understand the world comprehensively by integrating rich information from different modalities, achieving remarkable performance improvements on various multimodal downstream tasks. However, deploying LVLMs is often problematic due to their massive computational/energy costs and carbon consumption, making it infeasible to adopt conventional iterative global pruning, which is costly due to computing the Hessian matrix of the entire large model for sparsification. Alternatively, several studies have recently proposed layer-wise pruning approaches to avoid the expensive computation of global pruning and efficiently compress model weights according to their importance within a layer. However, these methods often suffer from suboptimal model compression due to their lack of a global perspective. To address this limitation in recent efficient pruning methods for large models, we propose Efficient Coarse-to-Fine Layer-Wise Pruning (ECoFLaP), a two-stage coarse-to-fine weight pruning approach for LVLMs. We first determine the sparsity ratios of different layers or blocks by leveraging the global importance score, which is efficiently computed based on the zeroth-order approximation of the global model gradients. Then, the multimodal model performs layer-wise unstructured weight pruning. We validate our proposed method across various multi-modal and single-modal models and datasets, demonstrating significant performance improvements over prevalent pruning techniques in the high-sparsity regime.

Details

TMLR Journal 2024 Journal Article

Exposing and Addressing Cross-Task Inconsistency in Unified Vision-Language Models

  • Adyasha Maharana
  • Amita Kamath
  • Christopher Clark
  • Mohit Bansal
  • Aniruddha Kembhavi

As general purpose vision models get increasingly effective at a wide set of tasks, it is imperative that they be consistent across the tasks they support. Inconsistent AI models are considered brittle and untrustworthy by human users and are more challenging to incorporate into larger systems that take dependencies on their outputs. Measuring consistency between very heterogeneous tasks that might include outputs in different modalities is challenging since it is difficult to determine if the predictions are consistent with one another. As a solution, we introduce a benchmark dataset, CocoCON, where we create contrast sets by modifying test instances for multiple tasks in small but semantically meaningful ways to change the gold label and outline metrics for measuring if a model is consistent by ranking the original and perturbed instances across tasks. We find that state-of-the-art vision-language models suffer from a surprisingly high degree of inconsistent behavior across tasks, especially for more heterogeneous tasks. To alleviate this issue, we propose a rank correlation-based auxiliary training objective, computed over large automatically created cross-task contrast sets, that improves the multi-task consistency of large unified models while retaining their original accuracy on downstream tasks.

PDF Details

TMLR Journal 2024 Journal Article

FlexEControl: Flexible and Efficient Multimodal Control for Text-to-Image Generation

  • Xuehai He
  • Jian Zheng
  • Jacob Zhiyuan Fang
  • Robinson Piramuthu
  • Mohit Bansal
  • Vicente Ordonez
  • Gunnar A Sigurdsson
  • Nanyun Peng

Controllable text-to-image (T2I) diffusion models generate images conditioned on both text prompts and semantic inputs of other modalities like edge maps. Nevertheless, current controllable T2I methods commonly face challenges related to efficiency and faithfulness, especially when conditioning on multiple inputs from either the same or diverse modalities. In this paper, we propose a novel Flexible and Efficient method, FlexEControl, for controllable T2I generation. At the core of FlexEControl is a unique weight decomposition strategy, which allows for streamlined integration of various input types. This approach not only enhances the faithfulness of the generated image to the control, but also significantly reduces the computational overhead typically associated with multimodal conditioning. Our approach achieves a reduction of 41% in trainable parameters and 30% in memory usage compared with Uni-ControlNet. Moreover, it doubles data efficiency and can flexibly generate images under the guidance of multiple input conditions of various modalities.

PDF Details

TMLR Journal 2024 Journal Article

Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs?

  • Peter Hase
  • Thomas Hofweber
  • Xiang Zhou
  • Elias Stengel-Eskin
  • Mohit Bansal

The model editing problem concerns how language models should learn new facts about the world over time. While empirical research on model editing has drawn widespread attention, the conceptual foundations of model editing remain shaky -- perhaps unsurprisingly, since model editing is essentially belief revision, a storied problem in philosophy that has eluded succinct solutions for decades. Model editing nonetheless demands a solution, since we need to be able to control knowledge within language models. With this goal in mind, this paper critiques the standard formulation of the model editing problem and proposes a formal testbed for model editing research. We first describe 13 open problems with model editing, based on challenges with (1) defining the problem, (2) developing benchmarks, and (3) assuming LLMs have editable beliefs in the first place. Many of the challenges are extremely difficult to address, e.g. determining far-reaching consequences of edits, labeling probabilistic entailments between facts, and updating beliefs of agent simulators. Next, we introduce a semi-synthetic dataset for model editing based on Wikidata, where we can evaluate edits against labels given by an idealized Bayesian agent. This enables us to say exactly how belief revision in language models falls short of a desirable epistemic standard. We encourage further research exploring settings where such a gold standard can be compared against.

PDF Details

NeurIPS Conference 2024 Conference Paper

GTBench: Uncovering the Strategic Reasoning Capabilities of LLMs via Game-Theoretic Evaluations

  • Jinhao Duan
  • Renming Zhang
  • James Diffenderfer
  • Bhavya Kailkhura
  • Lichao Sun
  • Elias Stengel-Eskin
  • Mohit Bansal
  • Tianlong Chen

As Large Language Models (LLMs) are integrated into critical real-world applications, their strategic and logical reasoning abilities are increasingly crucial. This paper evaluates LLMs' reasoning abilities in competitive environments through game-theoretic tasks, e. g. , board and card games that require pure logic and strategic reasoning to compete with opponents. We first propose GTBench, a language-driven environment composing 10 widely-recognized tasks, across a comprehensive game taxonomy: complete versus incomplete information, dynamic versus static, and probabilistic versus deterministic scenarios. Then, we (1) Characterize the game-theoretic reasoning of LLMs; and (2) Perform LLM-vs. -LLM competitions as reasoning evaluation. We observe that (1) LLMs have distinct behaviors regarding various gaming scenarios; for example, LLMs fail in complete and deterministic games yet they are competitive in probabilistic gaming scenarios; (2) Most open-source LLMs, e. g. , CodeLlama-34b-Instruct and Llama-2-70b-chat, are less competitive than commercial LLMs, e. g. , GPT-4, in complex games, yet the recently released Llama-3-70b-Instruct makes up for this shortcoming. In addition, code-pretraining greatly benefits strategic reasoning, while advanced reasoning methods such as Chain-of-Thought (CoT) and Tree-of-Thought (ToT) do not always help. We further characterize the game-theoretic properties of LLMs, such as equilibrium and Pareto Efficiency in repeated games. Detailed error profiles are provided for a better understanding of LLMs' behavior. We hope our research provides standardized protocols and serves as a foundation to spur further explorations in the strategic reasoning of LLMs.

PDF Details DOI

TMLR Journal 2024 Journal Article

INSPIRE: Incorporating Diverse Feature Preferences in Recourse

  • Prateek Yadav
  • Peter Hase
  • Mohit Bansal

Most recourse generation approaches optimize for indirect distance-based metrics like diversity, proximity, and sparsity, or a shared cost function across all users. A shared cost function in particular is an unrealistic assumption because users can have diverse feature preferences (FPs), i.e. the features they are willing to act upon to obtain recourse. In this work, we propose a novel method, INSPIRE to incorporate diverse feature preferences in both recourse generation and evaluation procedures by focusing on the cost incurred by a user when opting for a recourse. To achieve this, we first propose an objective function, Expected Minimum Cost (EMC) based on two key ideas: (1) the user should be comfortable adopting at least one solution when presented with multiple options, and (2) we can provide users with multiple options that cover a wide variety of FPs when the user's FPs are unknown. To optimize for EMC, we propose a novel discrete optimization algorithm, Cost-Optimized Local Search (COLS), that is guaranteed to improve the quality of the recourse set over iterations. Next, we propose a cost-based evaluation procedure that computes user satisfaction by simulating each user's cost function and then computing the incurred cost for the provided recourse set. Experiments on popular real-world datasets demonstrate that our method is more fair compared to baselines and satisfies up to 25.9% more users. We also show that our method is robust to misspecifications of the cost function distribution. Our code is available at \href{https://github.com/prateeky2806/EMC-COLS-recourse}{https://github.com/prateeky2806/EMC-COLS-recourse}.

PDF Details

NeurIPS Conference 2024 Conference Paper

LACIE: Listener-Aware Finetuning for Calibration in Large Language Models

  • Elias Stengel-Eskin
  • Peter Hase
  • Mohit Bansal

When answering questions, large language models (LLMs) can convey not only an answer to the question, but a level of confidence about the answer being correct. This includes explicit markers of confidence (e. g. giving a numeric confidence score) as well as implicit markers, like using an authoritative tone or elaborating with additional knowledge of a subject. For LLMs to be trustworthy sources of knowledge, the confidence they convey should match their actual expertise on a topic; however, this is currently not the case, with most models tending towards overconfidence. To calibrate both implicit and explicit confidence markers, we introduce a pragmatic, listener-aware finetuning method (LACIE) that directly models the listener, considering not only whether an answer is right, but whether it will be accepted by a listener. Specifically, we cast calibration as a preference optimization problem, creating data via a two-agent speaker-listener game, where a speaker model’s outputs are judged by a simulated listener. We then finetune three different LLMs (Mistral-7B, Llama3-8B, Llama3-70B) with LACIE, and show that the models resulting from this multi-agent optimization are better calibrated on TriviaQA with respect to a simulated listener. Crucially, these trends transfer to human listeners, helping them correctly predict model correctness: we conduct a human evaluation where annotators accept or reject an LLM’s answers to trivia questions, finding that training with LACIE results in 47% fewer incorrect answers being accepted while maintaining the same level of acceptance for correct answers. Furthermore, LACIE generalizes to another dataset, resulting in a large increase in truthfulness on TruthfulQA when trained on TriviaQA. Our analysis indicates that LACIE leads to a better separation in confidence between correct and incorrect examples. Qualitatively, we find that a LACIE-trained model hedges more when uncertain and adopts implicit cues to signal certainty when it is correct, such as using an authoritative tone or including details. Finally, finetuning with our listener- aware method leads to an emergent increase in model abstention (e. g. saying “I don’t know”) for answers that are likely to be wrong, trading recall for precision.

PDF Details DOI

ICML Conference 2024 Conference Paper

MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models

  • Justin Chih-Yao Chen
  • Swarnadeep Saha
  • Elias Stengel-Eskin
  • Mohit Bansal

Multi-agent interactions between Large Language Model (LLM) agents have shown major improvements on diverse reasoning tasks. However, these involve long generations from multiple models across several rounds, making them expensive. Moreover, these multi-agent approaches fail to provide a final, single model for efficient inference. To address this, we introduce MAGDi, a new method for structured distillation of the reasoning interactions between multiple LLMs into smaller LMs. MAGDi teaches smaller models by representing multi-agent interactions as graphs, augmenting a base student model with a graph encoder, and distilling knowledge using three objective functions: next-token prediction, a contrastive loss between correct and incorrect reasoning, and a graph-based objective to model the interaction structure. Experiments on seven widely used commonsense and math reasoning benchmarks show that MAGDi improves the reasoning capabilities of smaller models, outperforming several methods that distill from a single teacher and multiple teachers. Moreover, MAGDi also demonstrates an order of magnitude higher efficiency over its teachers. We conduct extensive analyses to show that MAGDi (1) enhances the generalizability to out-of-domain tasks, (2) scales positively with the size and strength of the base student model, and (3) obtains larger improvements (via our multi-teacher training) when applying self-consistency – an inference technique that relies on model diversity.

Details

ICLR Conference 2024 Conference Paper

Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy

  • Pingzhi Li
  • Zhenyu Zhang 0015
  • Prateek Yadav
  • Yi-Lin Sung
  • Yu Cheng 0001
  • Mohit Bansal
  • Tianlong Chen 0001

Sparsely activated Mixture-of-Experts (SMoE) has shown promise to scale up the learning capacity of neural networks, however, they have issues like: ($a$) $\textit{High Memory Usage,}$ due to duplication of the network layers into multiple copies as experts; and ($b$) $\textit{Redundancy in Experts,}$ as common learning-based routing policies suffer from representational collapse. Therefore, vanilla SMoE models are memory inefficient and non-scalable, especially for resource-constrained downstream scenarios. In this paper, we ask: Can we craft a compact SMoE model by consolidating expert information? What is the best recipe to merge multiple experts into fewer but more knowledgeable experts? Our pilot investigation reveals that conventional model merging methods fail to be effective in such expert merging for SMoE. The potential reasons are: ($1$) redundant information overshadows critical experts; ($2$) appropriate neuron permutation for each expert is missing to bring all of them in alignment. To address these challenges, we propose a novel merging algorithm for SMoE, $\textit{i.e.}$, $\texttt{M-SMoE}$, which leverages routing statistics to guide expert merging. Specifically, it starts with neuron permutation alignment for experts; then, dominant experts and their "group members" are formed based on routing policies; lastly, every expert group is merged into a single expert by utilizing each expert's activation frequency as their weight for merging, thus diminishing the impact of insignificant experts. Moreover, we draw an interesting observation that our proposed merging promotes a low dimensionality in the merged expert's weight space, naturally paving the way for additional compression. Hence, our final method, $\texttt{MC-SMoE}$ ($\textit{i.e.}$, Merge, then Compress SMoE), further decomposes the merged experts into low-rank and structural sparse alternatives. Extensive experiments across $8$ benchmarks validate the effectiveness of our proposals. For instance, our $\texttt{MC-SMoE}$ achieves up to $80\%$ memory and a $20\%$ FLOPs reduction, with virtually no loss in performance. Our code is provided as supplementary material.

Details

TMLR Journal 2024 Journal Article

Merging by Matching Models in Task Parameter Subspaces

  • Derek Tam
  • Mohit Bansal
  • Colin Raffel

Model merging aims to cheaply combine individual task-specific models into a single multitask model. In this work, we view past merging methods as leveraging different notions of a ''task parameter subspace'' in which models are matched before being merged. We connect the task parameter subspace of a given model to its loss landscape and formalize how this approach to model merging can be seen as solving a linear system of equations. While past work has generally been limited to linear systems that have a closed-form solution, we consider using the conjugate gradient method to find a solution. We show that using the conjugate gradient method can outperform closed-form solutions, enables merging via linear systems that are otherwise intractable to solve, and flexibly allows choosing from a wide variety of initializations and estimates for the ''task parameter subspace''. We ultimately demonstrate that our merging framework called ''Matching Models in their Task Parameter Subspace'' (MATS) achieves state-of-the-art results in multitask and intermediate-task model merging. We release all of the code and checkpoints used in our work.

PDF Details

ICML Conference 2024 Conference Paper

Position: TrustLLM: Trustworthiness in Large Language Models

  • Yue Huang 0001
  • Lichao Sun 0001
  • Haoran Wang 0005
  • Siyuan Wu 0001
  • Qihui Zhang
  • Yuan Li
  • Chujie Gao
  • Yixin Huang

Large language models (LLMs) have gained considerable attention for their excellent natural language processing capabilities. Nonetheless, these LLMs present many challenges, particularly in the realm of trustworthiness. This paper introduces TrustLLM, a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions. Specifically, we first propose a set of principles for trustworthy LLMs that span eight different dimensions. Based on these principles, we further establish a benchmark across six dimensions including truthfulness, safety, fairness, robustness, privacy, and machine ethics. We then present a study evaluating 16 mainstream LLMs in TrustLLM, consisting of over 30 datasets. Our findings firstly show that in general trustworthiness and capability (i. e. , functional effectiveness) are positively related. Secondly, our observations reveal that proprietary LLMs generally outperform most open-source counterparts in terms of trustworthiness, raising concerns about the potential risks of widely accessible open-source LLMs. However, a few open-source LLMs come very close to proprietary ones, suggesting that open-source models can achieve high levels of trustworthiness without additional mechanisms like moderator, offering valuable insights for developers in this field. Thirdly, it is important to note that some LLMs may be overly calibrated towards exhibiting trustworthiness, to the extent that they compromise their utility by mistakenly treating benign prompts as harmful and consequently not responding. Besides these observations, we’ve uncovered key insights into the multifaceted trustworthiness in LLMs. We emphasize the importance of ensuring transparency not only in the models themselves but also in the technologies that underpin trustworthiness. We advocate that the establishment of an AI alliance between industry, academia, the open-source community to foster collaboration is imperative to advance the trustworthiness of LLMs.

Details

ICML Conference 2024 Conference Paper

ReGAL: Refactoring Programs to Discover Generalizable Abstractions

  • Elias Stengel-Eskin
  • Archiki Prasad
  • Mohit Bansal

While large language models (LLMs) are increasingly being used for program synthesis, they lack the global view needed to develop useful abstractions; they generally predict programs one at a time, often repeating the same functionality. Generating redundant code from scratch is both inefficient and error-prone. To address this, we propose Refactoring for Generalizable Abstraction Learning (ReGAL), a gradient-free method for learning a library of reusable functions via code refactorization, i. e. , restructuring code without changing its execution output. ReGAL learns from a small set of existing programs, iteratively verifying and refining its abstractions via execution. We find that the shared function libraries discovered by ReGAL make programs easier to predict across diverse domains. On five datasets – LOGO graphics generation, Date reasoning, TextCraft (a Minecraft-based text-game) MATH, and TabMWP – both open-source and proprietary LLMs improve in accuracy when predicting programs with REGAL functions. For CodeLlama-13B, REGAL results in absolute accuracy increases of 11. 5% on LOGO, 26. 1% on date understanding, and 8. 1% on TextCraft, out-performing GPT-3. 5 in two of three domains. Our analysis reveals REGAL’s abstractions encapsulate frequently-used subroutines as well as environment dynamics.

Details

ICLR Conference 2024 Conference Paper

Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models

  • Archiki Prasad
  • Elias Stengel-Eskin
  • Mohit Bansal

An increasing number of vision-language tasks can be handled with little to no training, i.e., in a zero and few-shot manner, by marrying large language models (LLMs) to vision encoders, resulting in large vision-language models (LVLMs). While this has huge upsides, such as not requiring training data or custom architectures, how an input is presented to an LVLM can have a major impact on zero-shot model performance. In particular, inputs phrased in an underspecified way can result in incorrect answers due to factors like missing visual information, complex implicit reasoning, or linguistic ambiguity. Therefore, adding visually-grounded information to the input as a preemptive clarification should improve model performance by reducing underspecification, e.g., by localizing objects and disambiguating references. Similarly, in the VQA setting, changing the way questions are framed can make them easier for models to answer. To this end, we present **Rep**hrase, **A**ugment and **Re**ason (RepARe), a gradient-free framework that extracts salient details about the image using the underlying LVLM as a captioner and reasoner, in order to propose modifications to the original question. We then use the LVLM’s confidence over a generated answer as an unsupervised scoring function to select the rephrased question most likely to improve zero-shot performance. Focusing on three visual question answering tasks, we show that RepARe can result in a 3.85% (absolute) increase in zero-shot accuracy on VQAv2, 6.41%, and 7.94% points increase on A-OKVQA, and VizWiz respectively. Additionally, we find that using gold answers for oracle question candidate selection achieves a substantial gain in VQA accuracy by up to 14.41%. Through extensive analysis, we demonstrate that outputs from RepARe increase syntactic complexity, and effectively utilize vision-language interaction and the frozen LLM.

Details

NeurIPS Conference 2024 Conference Paper

SELMA: Learning and Merging Skill-Specific Text-to-Image Experts with Auto-Generated Data

  • Jialu Li
  • Jaemin Cho
  • Yi-Lin Sung
  • Jaehong Yoon
  • Mohit Bansal

Recent text-to-image (T2I) generation models have demonstrated impressive capabilities in creating images from text descriptions. However, these T2I generation models often fail to generate images that precisely match the details of the text inputs, such as incorrect spatial relationship or missing objects. In this paper, we introduce SELMA: Skill-Specific Expert Learning and Merging with Auto-Generated Data, a novel paradigm to improve the faithfulness of T2I models by fine-tuning models on automatically generated, multi-skill image-text datasets, with skill-specific expert learning and merging. First, SELMA leverages an LLM’s in-context learning capability to generate multiple datasets of text prompts that can teach different skills, and then generates the images with a T2I model based on the prompts. Next, SELMA adapts the T2I model to the new skills by learning multiple single-skill LoRA (low-rank adaptation) experts followed by expert merging. Our independent expert fine-tuning specializes multiple models for different skills, and expert merging helps build a joint multi-skill T2I model that can generate faithful images given diverse text prompts, while mitigating the knowledge conflict from different datasets. We empirically demonstrate that SELMA significantly improves the semantic alignment and text faithfulness of state-of-the-art T2I diffusion models on multiple benchmarks (+2. 1% on TIFA and +6. 9% on DSG), human preference metrics (PickScore, ImageReward, and HPS), as well as human evaluation. Moreover, fine-tuning with image-text pairs auto-collected via SELMA shows comparable performance to fine-tuning with ground truth data. Lastly, we show that fine-tuning with images from a weaker T2I model can help improve the generation quality of a stronger T2I model, suggesting promising weak-to-strong generalization in T2I models. We provide code in the supplementary materials.

PDF Details DOI

TMLR Journal 2024 Journal Article

Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation

  • Vaidehi Patil
  • Yi-Lin Sung
  • Peter Hase
  • Jie Peng
  • Tianlong Chen
  • Mohit Bansal

Large Language Models (LLMs) trained on massive datasets may inadvertently acquire sensitive information such as personal details and potentially harmful content. This risk is further heightened in multimodal LLMs (aka MLLMs) as they integrate information from multiple modalities (image and text). Adversaries can exploit this stored knowledge by crafting inputs across modalities to extract sensitive details. Evaluating how effectively MLLMs can forget such information (targeted unlearning) necessitates the creation of high-quality, well-annotated image-text pairs. While significant research has addressed the creation of datasets for unlearning within LLMs, it has primarily concentrated on text modality. Creation of analogous datasets for multimodal data and models remain an understudied area. To address this gap, we first introduce a multimodal unlearning benchmark, UnLOK-VQA (Unlearning Outside Knowledge VQA), as well as an “attack and-defense” framework to evaluate methods for deleting specific multimodal knowledge from MLLMs. Our dataset generation process involves an automated pipeline to create samples of varied proximity levels to the target data point for evaluation of generalization and specificity, followed by manual filtering to retain only the high-quality data points. We use this process to extend a visual question-answering dataset for evaluating multimodal information deletion. Next, we present a comprehensive unlearning evaluation involving an attack-and-defense framework consisting of four white box and three blackbox attacks against six unlearning defense objectives. We also design a whitebox attack based on the interpretability of hidden states in LLMs motivated by past work. Our experimental results demonstrate that multimodal extraction attacks (with an attack success rate of 45.5%) are more successful than either image-only (32%) or text-only attacks (39%). The best overall defense mechanism, which removes answer information from internal model hidden states, reduces the success rate of multimodal attack to 15.7%. Furthermore, our findings suggest that larger models exhibit greater resilience to attacks, implying that model scaling could be a valuable strategy for enhancing robustness and developing safer models. UnLOK-VQA thus facilitates a comprehensive evaluation of unlearning in MLLMs and serves as a challenging benchmark for future research in unlearning.

PDF Details

TMLR Journal 2024 Journal Article

Vision-and-Language Navigation Today and Tomorrow: A Survey in the Era of Foundation Models

  • Yue Zhang
  • Ziqiao Ma
  • Jialu Li
  • Yanyuan Qiao
  • Zun Wang
  • Joyce Chai
  • Qi Wu
  • Mohit Bansal

Vision-and-Language Navigation (VLN) has gained increasing attention over recent years and many approaches have emerged to advance their development. The remarkable achievements of foundation models have shaped the challenges and proposed methods for VLN research. In this survey, we provide a top-down review that adopts a principled framework for embodied planning and reasoning, and emphasizes the current methods and future opportunities leveraging foundation models to address VLN challenges. We hope our in-depth discussions could provide valuable resources and insights: on one hand, to document the progress and explore opportunities and potential roles for foundation models in this field, and on the other, to organize different challenges and solutions in VLN to foundation model researchers.

PDF Details

AAAI Conference 2024 Conference Paper

VLN-Video: Utilizing Driving Videos for Outdoor Vision-and-Language Navigation

  • Jialu Li
  • Aishwarya Padmakumar
  • Gaurav Sukhatme
  • Mohit Bansal

Outdoor Vision-and-Language Navigation (VLN) requires an agent to navigate through realistic 3D outdoor environments based on natural language instructions. The performance of existing VLN methods is limited by insufficient diversity in navigation environments and limited training data. To address these issues, we propose VLN-Video, which utilizes the diverse outdoor environments present in driving videos in multiple cities in the U.S. augmented with automatically generated navigation instructions and actions to improve outdoor VLN performance. VLN-Video combines the best of intuitive classical approaches and modern deep learning techniques, using template infilling to generate grounded non-repetitive navigation instructions, combined with an image rotation similarity based navigation action predictor to obtain VLN style data from driving videos for pretraining deep learning VLN models. We pre-train the model on the Touchdown dataset and our video-augmented dataset created from driving videos with three proxy tasks: Masked Language Modeling, Instruction and Trajectory Matching, and Next Action Prediction, so as to learn temporally-aware and visually-aligned instruction representations. The learned instruction representation is adapted to the state-of-the-art navigation agent when fine-tuning on the Touchdown dataset. Empirical results demonstrate that VLN-Video significantly outperforms previous state-of-the-art models by 2.1% in task completion rate, achieving a new state-of-the-art on the Touchdown dataset.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Adaptive Contextual Perception: How To Generalize To New Backgrounds and Ambiguous Objects

  • Zhuofan Ying
  • Peter Hase
  • Mohit Bansal

Biological vision systems make adaptive use of context to recognize objects in new settings with novel contexts as well as occluded or blurry objects in familiar settings. In this paper, we investigate how vision models adaptively use context for out-of-distribution (OOD) generalization and leverage our analysis results to improve model OOD generalization. First, we formulate two distinct OOD settings where the contexts are either beneficial Object-Disambiguation or irrelevant Background-Invariance, reflecting the diverse contextual challenges faced in biological vision. We then analyze model performance in these two different OOD settings and demonstrate that models that excel in one setting tend to struggle in the other. Notably, prior works on learning causal features improve on one setting but hurt on the other. This underscores the importance of generalizing across both OOD settings, as this ability is crucial for both human cognition and robust AI systems. Next, to better understand the model properties contributing to OOD generalization, we use representational geometry analysis and our own probing methods to examine a population of models, and we discover that those with more factorized representations and appropriate feature weighting are more successful in handling Object-Disambiguation and Background-Invariance tests. We further validate these findings through causal intervention, manipulating representation factorization and feature weighting to demonstrate their causal effect on performance. Motivated by our analysis results, we propose new augmentation methods aimed at enhancing model generalization. The proposed methods outperform strong baselines, yielding improvements in both in-distribution and OOD tests. We conclude that, in order to replicate the generalization abilities of biological vision, computer vision models must have factorized object vs. background representations and appropriately weigh both kinds of features.

PDF Details

NeurIPS Conference 2023 Conference Paper

Any-to-Any Generation via Composable Diffusion

  • Zineng Tang
  • Ziyi Yang
  • Chenguang Zhu
  • Michael Zeng
  • Mohit Bansal

We present Composable Diffusion (CoDi), a novel generative model capable of generating any combination of output modalities, such as language, image, video, or audio, from any combination of input modalities. Unlike existing generative AI systems, CoDi can generate multiple modalities in parallel and its input is not limited to a subset of modalities like text or image. Despite the absence of training datasets for many combinations of modalities, we propose to align modalities in both the input and output space. This allows CoDi to freely condition on any input combination and generate any group of modalities, even if they are not present in the training data. CoDi employs a novel composable generation strategy which involves building a shared multimodal space by bridging alignment in the diffusion process, enabling the synchronized generation of intertwined modalities, such as temporally aligned video and audio. Highly customizable and flexible, CoDi achieves strong joint-modality generation quality, and outperforms or is on par with the unimodal state-of-the-art for single-modality synthesis.

PDF Details

TMLR Journal 2023 Journal Article

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

  • Aarohi Srivastava
  • Abhinav Rastogi
  • Abhishek Rao
  • Abu Awal Md Shoeb
  • Abubakar Abid
  • Adam Fisch
  • Adam R. Brown
  • Adam Santoro

Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabilities are as yet poorly characterized. In order to inform future research, prepare for disruptive new model capabilities, and ameliorate socially harmful effects, it is vital that we understand the present and near-future capabilities and limitations of language models. To address this challenge, we introduce the Beyond the Imitation Game benchmark (BIG- bench). BIG-bench currently consists of 204 tasks, contributed by 450 authors across 132 institutions. Task topics are diverse, drawing problems from linguistics, childhood develop- ment, math, common-sense reasoning, biology, physics, social bias, software development, and beyond. BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models. We evaluate the behavior of OpenAI's GPT models, Google- internal dense transformer architectures, and Switch-style sparse transformers on BIG-bench, across model sizes spanning millions to hundreds of billions of parameters. In addition, a team of human expert raters performed all tasks in order to provide a strong baseline. Findings include: model performance and calibration both improve with scale, but are poor in absolute terms (and when compared with rater performance); performance is remarkably similar across model classes, though with benefits from sparsity; tasks that improve gradually and predictably commonly involve a large knowledge or memorization component, whereas tasks that exhibit "breakthrough" behavior at a critical scale often involve multiple steps or components, or brittle metrics; social bias typically increases with scale in settings with ambiguous context, but this can be improved with prompting.

PDF Details

NeurIPS Conference 2023 Conference Paper

Can Language Models Teach? Teacher Explanations Improve Student Performance via Personalization

  • Swarnadeep Saha
  • Peter Hase
  • Mohit Bansal

A hallmark property of explainable AI models is the ability to teach other agents, communicating knowledge of how to perform a task. While Large Language Models (LLMs) perform complex reasoning by generating explanations for their predictions, it is unclear whether they also make good teachers for weaker agents. To address this, we consider a student-teacher framework between two LLM agents and study if, when, and how the teacher should intervene with natural language explanations to improve the student’s performance. Since communication is expensive, we define a budget such that the teacher only communicates explanations for a fraction of the data, after which the student should perform well on its own. We decompose the teaching problem along four axes: (1) if teacher’s test time in- tervention improve student predictions, (2) when it is worth explaining a data point, (3) how the teacher should personalize explanations to better teach the student, and (4) if teacher explanations also improve student performance on future unexplained data. We first show that teacher LLMs can indeed intervene on student reasoning to improve their performance. Next, inspired by the Theory of Mind abilities of effective teachers, we propose building two few-shot mental models of the student. The first model defines an Intervention Function that simulates the utility of an intervention, allowing the teacher to intervene when this utility is the highest and improving student performance at lower budgets. The second model enables the teacher to personalize explanations for a particular student and outperform unpersonalized teachers. We also demonstrate that in multi-turn interactions, teacher explanations generalize and learning from explained data improves student performance on future unexplained data. Finally, we also verify that misaligned teachers can lower student performance to random chance by intentionally misleading them.

PDF Details

NeurIPS Conference 2023 Conference Paper

Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models

  • Peter Hase
  • Mohit Bansal
  • Been Kim
  • Asma Ghandeharioun

Language models learn a great quantity of factual information during pretraining, and recent work localizes this information to specific model weights like mid-layer MLP weights. In this paper, we find that we can change how a fact is stored in a model by editing weights that are in a different location than where existing methods suggest that the fact is stored. This is surprising because we would expect that localizing facts to specific model parameters would tell us where to manipulate knowledge in models, and this assumption has motivated past work on model editing methods. Specifically, we show that localization conclusions from representation denoising (also known as Causal Tracing) do not provide any insight into which model MLP layer would be best to edit in order to override an existing stored fact with a new one. This finding raises questions about how past work relies on Causal Tracing to select which model layers to edit. Next, we consider several variants of the editing problem, including erasing and amplifying facts. For one of our editing problems, editing performance does relate to localization results from representation denoising, but we find that which layer we edit is a far better predictor of performance. Our results suggest, counterintuitively, that better mechanistic understanding of how pretrained language models work may not always translate to insights about how to best change their behavior.

PDF Details

IJCAI Conference 2023 Conference Paper

On Conditional and Compositional Language Model Differentiable Prompting

  • Jonathan Pilault
  • Can Liu
  • Mohit Bansal
  • Markus Dreyer

Prompts have been shown to be an effective method to adapt a frozen Pretrained Language Model (PLM) to perform well on downstream tasks. Prompts can be represented by a human-engineered word sequence or by a learned continuous embedding. In this work, we investigate conditional and compositional differentiable prompting. We propose a new model, Prompt Production System (ProPS), which learns to transform task instructions or input metadata, into continuous prompts that elicit task-specific outputs from the PLM. Our model uses a modular network structure based on our neural formulation of Production Systems, which allows the model to learn discrete rules -- neural functions that learn to specialize in transforming particular prompt input patterns, making it suitable for compositional transfer learning and few-shot learning. We present extensive empirical and theoretical analysis and show that ProPS consistently surpasses other PLM adaptation techniques, and often improves upon fully fine-tuned models, on compositional generalization tasks, controllable summarization and multilingual translation, while needing fewer trainable parameters.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigation

  • Jialu Li
  • Mohit Bansal

Vision-and-Language Navigation requires the agent to follow language instructions to navigate through 3D environments. One main challenge in Vision-and-Language Navigation is the limited availability of photorealistic training environments, which makes it hard to generalize to new and unseen environments. To address this problem, we propose PanoGen, a generation method that can potentially create an infinite number of diverse panoramic environments conditioned on text. Specifically, we collect room descriptions by captioning the room images in existing Matterport3D environments, and leverage a state-of-the-art text-to-image diffusion model to generate the new panoramic environments. We use recursive outpainting over the generated images to create consistent 360-degree panorama views. Our new panoramic environments share similar semantic information with the original environments by conditioning on text descriptions, which ensures the co-occurrence of objects in the panorama follows human intuition, and creates enough diversity in room appearance and layout with image outpainting. Lastly, we explore two ways of utilizing PanoGen in VLN pre-training and fine-tuning. We generate instructions for paths in our PanoGen environments with a speaker built on a pre-trained vision-and-language model for VLN pre-training, and augment the visual observation with our panoramic environments during agents' fine-tuning to avoid overfitting to seen environments. Empirically, learning with our PanoGen environments achieves the new state-of-the-art on the Room-to-Room, Room-for-Room, and CVDN datasets. Besides, we find that pre-training with our PanoGen speaker data is especially effective for CVDN, which has under-specified instructions and needs commonsense knowledge to reach the target. Lastly, we show that the agent can benefit from training with more generated panoramic environments, suggesting promising results for scaling up the PanoGen environments to enhance agents' generalization to unseen environments.

PDF Details

NeurIPS Conference 2023 Conference Paper

Paxion: Patching Action Knowledge in Video-Language Foundation Models

  • Zhenhailong Wang
  • Ansel Blume
  • Sha Li
  • Genglin Liu
  • Jaemin Cho
  • Zineng Tang
  • Mohit Bansal
  • Heng Ji

Action knowledge involves the understanding of textual, visual, and temporal aspects of actions. We introduce the Action Dynamics Benchmark (ActionBench) containing two carefully designed probing tasks: Action Antonym and Video Reversal, which targets multimodal alignment capabilities and temporal understanding skills of the model, respectively. Despite recent video-language models’ (VidLM) impressive performance on various benchmark tasks, our diagnostic tasks reveal their surprising deficiency (near-random performance) in action knowledge, suggesting that current models rely on object recognition abilities as a shortcut for action understanding. To remedy this, we propose a novel framework, Paxion, along with a new Discriminative Video Dynamics Modeling (DVDM) objective. The Paxion framework utilizes a Knowledge Patcher network to encode new action knowledge and a Knowledge Fuser component to integrate the Patcher into frozen VidLMs without compromising their existing capabilities. Due to limitations of the widely-used Video-Text Contrastive (VTC) loss for learning action knowledge, we introduce the DVDM objective to train the Knowledge Patcher. DVDM forces the model to encode the correlation between the action text and the correct ordering of video frames. Our extensive analyses show that Paxion and DVDM together effectively fill the gap in action knowledge understanding (~50% → 80%), while maintaining or improving performance on a wide spectrum of both object- and action-centric downstream tasks.

PDF Details

NeurIPS Conference 2023 Conference Paper

Self-Chained Image-Language Model for Video Localization and Question Answering

  • Shoubin Yu
  • Jaemin Cho
  • Prateek Yadav
  • Mohit Bansal

Recent studies have shown promising results on utilizing large pre-trained image-language models for video question answering. While these image-language models can efficiently bootstrap the representation learning of video-language models, they typically concatenate uniformly sampled video frames as visual inputs without explicit language-aware, temporal modeling. When only a portion of a video input is relevant to the language query, such uniform frame sampling can often lead to missing important visual cues. Although humans often find a video moment to focus on and rewind the moment to answer questions, training a query-aware video moment localizer often requires expensive annotations and high computational costs. To address this issue, we propose Self-Chained Video Localization-Answering (SeViLA), a novel framework that leverages a single image-language model (BLIP- 2) to tackle both temporal keyframe localization and question answering on videos. SeViLA framework consists of two modules: Localizer and Answerer, where both are parameter-efficiently fine-tuned from BLIP-2. We propose two ways of chaining these modules for cascaded inference and self-refinement. First, in the forward chain, the Localizer finds multiple language-aware keyframes in a video, which the Answerer uses to predict the answer. Second, in the reverse chain, the Answerer generates keyframe pseudo-labels to refine the Localizer, alleviating the need for expensive video moment localization annotations. Our SeViLA framework outperforms several strong baselines/previous works on five challenging video question answering and event prediction benchmarks, and achieves the state-of-the-art in both fine-tuning (NExT-QA and STAR) and zero-shot (NExT-QA, STAR, How2QA, and VLEP) settings. We show a comprehensive analysis of our framework, including the impact of Localizer, comparisons of Localizer with other temporal localization models, pre-training/self-refinement of Localizer, and varying the number of keyframes.

PDF Details

ICLR Conference 2023 Conference Paper

Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Trees

  • Swarnadeep Saha
  • Shiyue Zhang 0001
  • Peter Hase
  • Mohit Bansal

Current abstractive summarization models either suffer from a lack of clear interpretability or provide incomplete rationales by only highlighting parts of the source document. To this end, we propose the Summarization Program (SP), an interpretable modular framework consisting of an (ordered) list of binary trees, each encoding the step-by-step generative process of an abstractive summary sentence from the source document. A Summarization Program contains one root node per summary sentence, and a distinct tree connects each summary sentence (root node) to the document sentences (leaf nodes) from which it is derived, with the connecting nodes containing intermediate generated sentences. Edges represent different modular operations involved in summarization such as sentence fusion, compression, and paraphrasing. We first propose an efficient best-first search method over neural modules, SP-Search that identifies SPs for human summaries by directly optimizing for ROUGE scores. Next, using these programs as automatic supervision, we propose seq2seq models that generate Summarization Programs, which are then executed to obtain final summaries. We demonstrate that SP-Search effectively represents the generative process behind human summaries using modules that are typically faithful to their intended behavior. We also conduct a simulation study to show that Summarization Programs improve the interpretability of summarization models by allowing humans to better simulate model reasoning. Summarization Programs constitute a promising step toward interpretable and modular abstractive summarization, a complex task previously addressed primarily through blackbox end-to-end neural systems.

Details

NeurIPS Conference 2023 Conference Paper

TIES-Merging: Resolving Interference When Merging Models

  • Prateek Yadav
  • Derek Tam
  • Leshem Choshen
  • Colin A. Raffel
  • Mohit Bansal

Transfer learning – i. e. , further fine-tuning a pre-trained model on a downstream task – can confer significant advantages, including improved downstream performance, faster convergence, and better sample efficiency. These advantages have led to a proliferation of task-specific fine-tuned models, which typically can only perform a single task and do not benefit from one another. Recently, model merging techniques have emerged as a solution to combine multiple task-specific models into a single multitask model without performing additional training. However, existing merging methods often ignore the interference between parameters of different models, resulting in large performance drops when merging multiple models. In this paper, we demonstrate that prior merging techniques inadvertently lose valuable information due to two major sources of interference: (a) interference due to redundant parameter values and (b) disagreement on the sign of a given parameter’s values across models. To address this, we propose our method, TrIm, Elect Sign & Merge (TIES-Merging), which introduces three novel steps when merging models: (1) resetting parameters that only changed a small amount during fine-tuning, (2) resolving sign conflicts, and (3) merging only the parameters that are in alignment with the final agreed-upon sign. We find that TIES-Merging outperforms existing methods in diverse settings covering a range of modalities, domains, number of tasks, model sizes, architectures, and fine-tuning settings. We further analyze the impact of different types of interference on model parameters, highlight the importance of signs, and show that estimating the signs using the validation data could further improve performance.

PDF Details

NeurIPS Conference 2023 Conference Paper

Visual Programming for Step-by-Step Text-to-Image Generation and Evaluation

  • Jaemin Cho
  • Abhay Zala
  • Mohit Bansal

As large language models have demonstrated impressive performance in many domains, recent works have adopted language models (LMs) as controllers of visual modules for vision-and-language tasks. While existing work focuses on equipping LMs with visual understanding, we propose two novel interpretable/explainable visual programming frameworks for text-to-image (T2I) generation and evaluation. First, we introduce VPGen, an interpretable step-by-step T2I generation framework that decomposes T2I generation into three steps: object/count generation, layout generation, and image generation. We employ an LM to handle the first two steps (object/count generation and layout generation), by finetuning it on text-layout pairs. Our step-by-step T2I generation framework provides stronger spatial control than end-to-end models, the dominant approach for this task. Furthermore, we leverage the world knowledge of pretrained LMs, overcoming the limitation of previous layout-guided T2I works that can only handle predefined object classes. We demonstrate that our VPGen has improved control in counts/spatial relations/scales of objects than state-of-the-art T2I generation models. Second, we introduce VPEval, an interpretable and explainable evaluation framework for T2I generation based on visual programming. Unlike previous T2I evaluations with a single scoring model that is accurate in some skills but unreliable in others, VPEval produces evaluation programs that invoke a set of visual modules that are experts in different skills, and also provides visual+textual explanations of the evaluation results. Our analysis shows that VPEval provides a more human-correlated evaluation for skill-specific and open-ended prompts than widely used single model-based evaluation. We hope that our work encourages future progress on interpretable/explainable generation and evaluation for T2I models.

PDF Details

AAAI Conference 2022 Conference Paper

CAISE: Conversational Agent for Image Search and Editing

  • Hyounghun Kim
  • Doo Soon Kim
  • Seunghyun Yoon
  • Franck Dernoncourt
  • Trung Bui
  • Mohit Bansal

Demand for image editing has been increasing as users’ desire for expression is also increasing. However, for most users, image editing tools are not easy to use since the tools require certain expertise in photo effects and have complex interfaces. Hence, users might need someone to help edit their images, but having a personal dedicated human assistant for every user is impossible to scale. For that reason, an automated assistant system for image editing is desirable. Additionally, users want more image sources for diverse image editing works, and integrating an image search functionality into the editing tool is a potential remedy for this demand. Thus, we propose a dataset of an automated Conversational Agent for Image Search and Editing (CAISE). To our knowledge, this is the first dataset that provides conversational image search and editing annotations, where the agent holds a grounded conversation with users and helps them to search and edit images according to their requests. To build such a system, we first collect image search and editing conversations between pairs of annotators. The assistant-annotators are equipped with a customized image search and editing tool to address the requests from the user-annotators. The functions that the assistant-annotators conduct with the tool are recorded as executable commands, allowing the trained system to be useful for real-world application execution. We also introduce a generator-extractor baseline model for this task, which can adaptively select the source of the next token (i. e. , from the vocabulary or from textual/visual contexts) for the executable command. This serves as a strong starting point while still leaving a large human-machine performance gap for useful future work. Data and code are available: https: //github. com/hyounghk/CAISE.

PDF Details

NeurIPS Conference 2022 Conference Paper

Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning

  • Haokun Liu
  • Derek Tam
  • Mohammed Muqeeth
  • Jay Mohta
  • Tenghao Huang
  • Mohit Bansal
  • Colin A. Raffel

Few-shot in-context learning (ICL) enables pre-trained language models to perform a previously-unseen task without any gradient-based training by feeding a small number of training examples as part of the input. ICL incurs substantial computational, memory, and storage costs because it involves processing all of the training examples every time a prediction is made. Parameter-efficient fine-tuning (PEFT) (e. g. adapter modules, prompt tuning, sparse update methods, etc. ) offers an alternative paradigm where a small set of parameters are trained to enable a model to perform the new task. In this paper, we rigorously compare few-shot ICL and PEFT and demonstrate that the latter offers better accuracy as well as dramatically lower computational costs. Along the way, we introduce a new PEFT method called (IA)^3 that scales activations by learned vectors, attaining stronger performance while only introducing a relatively tiny amount of new parameters. We also propose a simple recipe based on the T0 model called T-Few that can be applied to new tasks without task-specific tuning or modifications. We validate the effectiveness of T-Few on completely unseen tasks by applying it to the RAFT benchmark, attaining super-human performance for the first time and outperforming the state-of-the-art by 6% absolute. All of the code used in our experiments will be publicly available.

PDF Details

ICLR Conference 2022 Conference Paper

How Much Can CLIP Benefit Vision-and-Language Tasks?

  • Sheng Shen 0001
  • Liunian Harold Li
  • Hao Tan 0002
  • Mohit Bansal
  • Anna Rohrbach
  • Kai-Wei Chang 0001
  • Zhewei Yao
  • Kurt Keutzer

Most existing Vision-and-Language (V&L) models rely on pre-trained visual encoders, using a relatively small set of manually-annotated data (as compared to web-crawled data), to perceive the visual world. However, it has been observed that large-scale pretraining usually can result in better generalization performance, e.g., CLIP (Contrastive Language-Image Pre-training), trained on a massive amount of image-caption pairs, has shown a strong zero-shot capability on various vision tasks. To further study the advantage brought by CLIP, we propose to use CLIP as the visual encoder in various V&L models in two typical scenarios: 1) plugging CLIP into task-specific fine-tuning; 2) combining CLIP with V&L pre-training and transferring to downstream tasks. We show that CLIP significantly outperforms widely-used visual encoders trained with in-domain annotated data, such as BottomUp-TopDown. We achieve competitive or better results on diverse V&L tasks, while establishing new state-of-the-art results on Visual Question Answering, Visual Entailment, and V&L Navigation tasks.

Details

NeurIPS Conference 2022 Conference Paper

Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners

  • Zhenhailong Wang
  • Manling Li
  • Ruochen Xu
  • Luowei Zhou
  • Jie Lei
  • Xudong Lin
  • Shuohang Wang
  • Ziyi Yang

The goal of this work is to build flexible video-language models that can generalize to various video-to-text tasks from few examples. Existing few-shot video-language learners focus exclusively on the encoder, resulting in the absence of a video-to-text decoder to handle generative tasks. Video captioners have been pretrained on large-scale video-language datasets, but they rely heavily on finetuning and lack the ability to generate text for unseen tasks in a few-shot setting. We propose VidIL, a few-shot Video-language Learner via Image and Language models, which demonstrates strong performance on few-shot video-to-text tasks without the necessity of pretraining or finetuning on any video datasets. We use image-language models to translate the video content into frame captions, object, attribute, and event phrases, and compose them into a temporal-aware template. We then instruct a language model, with a prompt containing a few in-context examples, to generate a target output from the composed content. The flexibility of prompting allows the model to capture any form of text input, such as automatic speech recognition (ASR) transcripts. Our experiments demonstrate the power of language models in understanding videos on a wide variety of video-language tasks, including video captioning, video question answering, video caption retrieval, and video future event prediction. Especially, on video future event prediction, our few-shot model significantly outperforms state-of-the-art supervised models trained on large-scale video datasets. Code and processed data are publicly available for research purposes at https: //github. com/MikeWangWZHL/VidIL.

PDF Details

NeurIPS Conference 2022 Conference Paper

LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning

  • Yi-Lin Sung
  • Jaemin Cho
  • Mohit Bansal

Fine-tuning large pre-trained models on downstream tasks has been adopted in a variety of domains recently. However, it is costly to update the entire parameter set of large pre-trained models. Although recently proposed parameter-efficient transfer learning (PETL) techniques allow updating a small subset of parameters (e. g. only using 2% of parameters) inside a pre-trained backbone network for a new task, they only reduce the training memory requirement by up to 30%. This is because the gradient computation for the trainable parameters still requires back-propagation through the large pre-trained backbone model. To address this, we propose Ladder Side-Tuning (LST), a new PETL technique that can reduce training memory requirements by more substantial amounts. Unlike existing parameter-efficient methods that insert additional parameters inside backbone networks, we train a ladder side network, a small and separate network that takes intermediate activations as input via shortcut connections (ladders) from backbone networks and makes predictions. LST has significantly lower memory requirements than previous methods, because it does not require back-propagation through the backbone network, but instead only through the side network and ladder connections. We evaluate our method with various models (T5 and CLIP-T5) on both natural language processing (GLUE) and vision-and-language (VQA, GQA, NLVR2, MSCOCO) tasks. LST saves 69% of the memory costs to fine-tune the whole network, while other methods only save 26% of that in similar parameter usages (hence, 2. 7x more memory savings). Moreover, LST achieves higher accuracy than Adapter and LoRA in a low-memory regime. To further show the advantage of this better memory efficiency, we also apply LST to larger T5 models (T5-large, T5-3B), attaining better GLUE performance than full fine-tuning and other PETL methods. The trend also holds in the experiments on vision-and-language tasks, where LST achieves similar accuracy to other PETL methods when training a similar number of parameters while also having 2. 7x more memory savings. Our code is available at: https: //github. com/ylsung/Ladder-Side-Tuning.

PDF Details

AAAI Conference 2022 Conference Paper

MuMuQA: Multimedia Multi-Hop News Question Answering via Cross-Media Knowledge Extraction and Grounding

  • Revant Gangi Reddy
  • Xilin Rui
  • Manling Li
  • Xudong Lin
  • Haoyang Wen
  • Jaemin Cho
  • Lifu Huang
  • Mohit Bansal

Recently, there has been an increasing interest in building question answering (QA) models that reason across multiple modalities, such as text and images. However, QA using images is often limited to just picking the answer from a predefined set of options. In addition, images in the real world, especially in news, have objects that are co-referential to the text, with complementary information from both modalities. In this paper, we present a new QA evaluation benchmark with 1, 384 questions over news articles that require crossmedia grounding of objects in images onto text. Specifically, the task involves multi-hop questions that require reasoning over image-caption pairs to identify the grounded visual object being referred to and then predicting a span from the news body text to answer the question. In addition, we introduce a novel multimedia data augmentation framework, based on cross-media knowledge extraction and synthetic question-answer generation, to automatically augment data that can provide weak supervision for this task. We evaluate both pipeline-based and end-to-end pretraining-based multimedia QA models on our benchmark, and show that they achieve promising performance, while considerably lagging behind human performance hence leaving large room for future work on this challenging new task.

PDF Details

NeurIPS Conference 2022 Conference Paper

TVLT: Textless Vision-Language Transformer

  • Zineng Tang
  • Jaemin Cho
  • Yixin Nie
  • Mohit Bansal

In this work, we present the Textless Vision-Language Transformer (TVLT), where homogeneous transformer blocks take raw visual and audio inputs for vision-and-language representation learning with minimal modality-specific design, and do not use text-specific modules such as tokenization or automatic speech recognition (ASR). TVLT is trained by reconstructing masked patches of continuous video frames and audio spectrograms (masked autoencoding) and contrastive modeling to align video and audio. TVLT attains performance comparable to its text-based counterpart on various multimodal tasks, such as visual question answering, image retrieval, video retrieval, and multimodal sentiment analysis, with 28x faster inference speed and only 1/3 of the parameters. Our findings suggest the possibility of learning compact and efficient visual-linguistic representations from low-level visual and audio signals without assuming the prior existence of text. Our code and checkpoints are available at: https: //github. com/zinengtang/TVLT

PDF Details

NeurIPS Conference 2022 Conference Paper

VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason Objectives

  • Zhuofan Ying
  • Peter Hase
  • Mohit Bansal

Many past works aim to improve visual reasoning in models by supervising feature importance (estimated by model explanation techniques) with human annotations such as highlights of important image regions. However, recent work has shown that performance gains from feature importance (FI) supervision for Visual Question Answering (VQA) tasks persist even with random supervision, suggesting that these methods do not meaningfully align model FI with human FI. In this paper, we show that model FI supervision can meaningfully improve VQA model accuracy as well as performance on several Right-for-the-Right-Reason (RRR) metrics by optimizing for four key model objectives: (1) accurate predictions given limited but sufficient information (Sufficiency); (2) max-entropy predictions given no important information (Uncertainty); (3) invariance of predictions to changes in unimportant features (Invariance); and (4) alignment between model FI explanations and human FI explanations (Plausibility). Our best performing method, Visual Feature Importance Supervision (VISFIS), outperforms strong baselines on benchmark VQA datasets in terms of both in-distribution and out-of-distribution accuracy. While past work suggests that the mechanism for improved accuracy is through improved explanation plausibility, we show that this relationship depends crucially on explanation faithfulness (whether explanations truly represent the model’s internal reasoning). Predictions are more accurate when explanations are plausible and faithful, and not when they are plausible but not faithful. Lastly, we show that, surprisingly, RRR metrics are not predictive of out-of-distribution model accuracy when controlling for a model’s in-distribution accuracy, which calls into question the value of these metrics for evaluating model reasoning.

PDF Details

NeurIPS Conference 2022 Conference Paper

WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language Models

  • Yonatan Bitton
  • Nitzan Bitton Guetta
  • Ron Yosef
  • Yuval Elovici
  • Mohit Bansal
  • Gabriel Stanovsky
  • Roy Schwartz

While vision-and-language models perform well on tasks such as visual question answering, they struggle when it comes to basic human commonsense reasoning skills. In this work, we introduce WinoGAViL: an online game of vision-and-language associations (e. g. , between werewolves and a full moon), used as a dynamic evaluation benchmark. Inspired by the popular card game Codenames, a spymaster gives a textual cue related to several visual candidates, and another player tries to identify them. Human players are rewarded for creating associations that are challenging for a rival AI model but still solvable by other human players. We use the game to collect 3. 5K instances, finding that they are intuitive for humans (>90% Jaccard index) but challenging for state-of-the-art AI models, where the best model (ViLT) achieves a score of 52%, succeeding mostly where the cue is visually salient. Our analysis as well as the feedback we collect from players indicate that the collected associations require diverse reasoning skills, including general knowledge, common sense, abstraction, and more. We release the dataset, the code and the interactive game, allowing future data collection that can be used to develop models with better association abilities.

PDF Details

AAAI Conference 2021 Conference Paper

Data Augmentation for Abstractive Query-Focused Multi-Document Summarization

  • Ramakanth Pasunuru
  • Asli Celikyilmaz
  • Michel Galley
  • Chenyan Xiong
  • Yizhe Zhang
  • Mohit Bansal
  • Jianfeng Gao

The progress in Query-focused Multi-Document Summarization (QMDS) has been limited by the lack of sufficient largescale high-quality training datasets. We present two QMDS training datasets, which we construct using two data augmentation methods: (1) transferring the commonly used singledocument CNN/Daily Mail summarization dataset to create the QMDSCNN dataset, and (2) mining search-query logs to create the QMDSIR dataset. These two datasets have complementary properties, i. e. , QMDSCNN has real summaries but queries are simulated, while QMDSIR has real queries but simulated summaries. To cover both these real summary and query aspects, we build abstractive end-to-end neural network models on the combined datasets that yield new state-of-theart transfer results on DUC datasets. We also introduce new hierarchical encoders that enable a more efficient encoding of the query together with multiple documents. Empirical results demonstrate that our data augmentation and encoding methods outperform baseline models on automatic metrics, as well as on human evaluations along multiple attributes.

PDF Details

NeurIPS Conference 2021 Conference Paper

Detecting Moments and Highlights in Videos via Natural Language Queries

  • Jie Lei
  • Tamara L Berg
  • Mohit Bansal

Detecting customized moments and highlights from videos given natural language (NL) user queries is an important but under-studied topic. One of the challenges in pursuing this direction is the lack of annotated data. To address this issue, we present the Query-based Video Highlights (QVHighlights) dataset. It consists of over 10, 000 YouTube videos, covering a wide range of topics, from everyday activities and travel in lifestyle vlog videos to social and political activities in news videos. Each video in the dataset is annotated with: (1) a human-written free-form NL query, (2) relevant moments in the video w. r. t. the query, and (3) five-point scale saliency scores for all query-relevant clips. This comprehensive annotation enables us to develop and evaluate systems that detect relevant moments as well as salient highlights for diverse, flexible user queries. We also present a strong baseline for this task, Moment-DETR, a transformer encoder-decoder model that views moment retrieval as a direct set prediction problem, taking extracted video and query representations as inputs and predicting moment coordinates and saliency scores end-to-end. While our model does not utilize any human prior, we show that it performs competitively when compared to well-engineered architectures. With weakly supervised pretraining using ASR captions, Moment-DETR substantially outperforms previous methods. Lastly, we present several ablations and visualizations of Moment-DETR. Data and code is publicly available at https: //github. com/jayleicn/moment_detr.

PDF Details

AAAI Conference 2021 Conference Paper

FIXMYPOSE: Pose Correctional Captioning and Retrieval

  • Hyounghun Kim
  • Abhay Zala
  • Graham Burri
  • Mohit Bansal

Interest in physical therapy and individual exercises such as yoga/dance has increased alongside the well-being trend, and people globally enjoy such exercises at home/office via video streaming platforms. However, such exercises are hard to follow without expert guidance. Even if experts can help, it is almost impossible to give personalized feedback to every trainee remotely. Thus, automated pose correction systems are required more than ever, and we introduce a new captioning dataset named FIXMYPOSE to address this need. We collect natural language descriptions of correcting a “current” pose to look like a “target” pose. To support a multilingual setup, we collect descriptions in both English and Hindi. The collected descriptions have interesting linguistic properties such as egocentric relations to the environment objects, analogous references, etc. , requiring an understanding of spatial relations and commonsense knowledge about postures. Further, to avoid ML biases, we maintain a balance across characters with diverse demographics, who perform a variety of movements in several interior environments (e. g. , homes, offices). From our FIXMYPOSE dataset, we introduce two tasks: the pose-correctional-captioning task and its reverse, the targetpose-retrieval task. During the correctional-captioning task, models must generate the descriptions of how to move from the current to the target pose image, whereas in the retrieval task, models should select the correct target pose given the initial pose and the correctional description. We present strong cross-attention baseline models (uni/multimodal, RL, multilingual) and also show that our baselines are competitive with other models when evaluated on other image-difference datasets. We also propose new task-specific metrics (objectmatch, body-part-match, direction-match) and conduct human evaluation for more reliable evaluation, and we demonstrate a large human-model performance gap suggesting room for promising future work. Finally, to verify the sim-to-real transfer of our FIXMYPOSE dataset, we collect a set of real images and show promising performance on these images. Data and code are available: https: //fixmypose-unc. github. io.

PDF Details

NeurIPS Conference 2021 Conference Paper

The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations

  • Peter Hase
  • Harry Xie
  • Mohit Bansal

Feature importance (FI) estimates are a popular form of explanation, and they are commonly created and evaluated by computing the change in model confidence caused by removing certain input features at test time. For example, in the standard Sufficiency metric, only the top-k most important tokens are kept. In this paper, we study several under-explored dimensions of FI explanations, providing conceptual and empirical improvements for this form of explanation. First, we advance a new argument for why it can be problematic to remove features from an input when creating or evaluating explanations: the fact that these counterfactual inputs are out-of-distribution (OOD) to models implies that the resulting explanations are socially misaligned. The crux of the problem is that the model prior and random weight initialization influence the explanations (and explanation metrics) in unintended ways. To resolve this issue, we propose a simple alteration to the model training process, which results in more socially aligned explanations and metrics. Second, we compare among five approaches for removing features from model inputs. We find that some methods produce more OOD counterfactuals than others, and we make recommendations for selecting a feature-replacement function. Finally, we introduce four search-based methods for identifying FI explanations and compare them to strong baselines, including LIME, Anchors, and Integrated Gradients. Through experiments with six diverse text classification datasets, we find that the only method that consistently outperforms random search is a Parallel Local Search (PLS) that we introduce. Improvements over the second best method are as large as 5. 4 points for Sufficiency and 17 points for Comprehensiveness.

PDF Details

ICML Conference 2021 Conference Paper

Unifying Vision-and-Language Tasks via Text Generation

  • Jaemin Cho 0001
  • Jie Lei 0003
  • Hao Tan 0002
  • Mohit Bansal

Existing methods for vision-and-language learning typically require designing task-specific architectures and objectives for each task. For example, a multi-label answer classifier for visual question answering, a region scorer for referring expression comprehension, and a language decoder for image captioning, etc. To alleviate these hassles, in this work, we propose a unified framework that learns different tasks in a single architecture with the same language modeling objective, i. e. , multimodal conditional text generation, where our models learn to generate labels in text based on the visual and textual inputs. On 7 popular vision-and-language benchmarks, including visual question answering, referring expression comprehension, visual commonsense reasoning, most of which have been previously modeled as discriminative tasks, our generative approach (with a single unified architecture) reaches comparable performance to recent task-specific state-of-the-art vision-and-language models. Moreover, our generative approach shows better generalization ability on questions that have rare answers. Also, we show that our framework allows multi-task learning in a single architecture with a single set of parameters, achieving similar performance to separately optimized single-task models. Our code is publicly available at: https: //github. com/j-min/VL-T5

Details

NeurIPS Conference 2021 Conference Paper

VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation

  • Linjie Li
  • Jie Lei
  • Zhe Gan
  • Licheng Yu
  • Yen-Chun Chen
  • Rohit Pillai
  • Yu Cheng
  • Luowei Zhou

Most existing video-and-language (VidL) research focuses on a single dataset, or multiple datasets of a single task. In reality, a truly useful VidL system is expected to be easily generalizable to diverse tasks, domains, and datasets. To facilitate the evaluation of such systems, we introduce Video-And-Language Understanding Evaluation (VALUE) benchmark, an assemblage of 11 VidL datasets over 3 popular tasks: (i) text-to-video retrieval; (ii) video question answering; and (iii) video captioning. VALUE benchmark aims to cover a broad range of video genres, video lengths, data volumes, and task difficulty levels. Rather than focusing on single-channel videos with visual information only, VALUE promotes models that leverage information from both video frames and their associated subtitles, as well as models that share knowledge across multiple tasks. We evaluate various baseline methods with and without large-scale VidL pre-training, and systematically investigate the impact of video input channels, fusion methods, and different video representations. We also study the transferability between tasks, and conduct multi-task learning under different settings. The significant gap between our best model and human performance calls for future study for advanced VidL models. VALUE is available at https: //value-benchmark. github. io/.

PDF Details

NeurIPS Conference 2021 Conference Paper

VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer

  • Zineng Tang
  • Jaemin Cho
  • Hao Tan
  • Mohit Bansal

Since visual perception can give rich information beyond text descriptions for world understanding, there has been increasing interest in leveraging visual grounding for language learning. Recently, vokenization (Tan and Bansal, 2020) has attracted attention by using the predictions of a text-to-image retrieval model as labels for language model supervision. Despite its success, the method suffers from approximation error of using finite image labels and the lack of vocabulary diversity of a small image-text dataset. To overcome these limitations, we present VidLanKD, a video-language knowledge distillation method for improving language understanding. We train a multi-modal teacher model on a video-text dataset, and then transfer its knowledge to a student language model with a text dataset. To avoid approximation error, we propose to use different knowledge distillation objectives. In addition, the use of a large-scale video-text dataset helps learn diverse and richer vocabularies. In our experiments, VidLanKD achieves consistent improvements over text-only language models and vokenization models, on several downstream language understanding tasks including GLUE, SQuAD, and SWAG. We also demonstrate the improved world knowledge, physical reasoning, and temporal reasoning capabilities of our model by evaluating on the GLUE-diagnostics, PIQA, and TRACIE datasets. Lastly, we present comprehensive ablation studies as well as visualizations of the learned text-to-video grounding results of our teacher and student language models.

PDF Details

AAAI Conference 2020 Conference Paper

AvgOut: A Simple Output-Probability Measure to Eliminate Dull Responses

  • Tong Niu
  • Mohit Bansal

Many sequence-to-sequence dialogue models tend to generate safe, uninformative responses. There have been various useful efforts on trying to eliminate them. However, these approaches either improve decoding algorithms during inference, rely on hand-crafted features, or employ complex models. In our work, we build dialogue models that are dynamically aware of what utterances or tokens are dull without any feature-engineering. Specifically, we start with a simple yet effective automatic metric, AVGOUT, which calculates the average output probability distribution of all time steps on the decoder side during training. This metric directly estimates which tokens are more likely to be generated, thus making it a faithful evaluation of the model diversity (i. e. , for diverse models, the token probabilities should be more evenly distributed rather than peaked at a few dull tokens). We then leverage this novel metric to propose three models that promote diversity without losing relevance. The first model, MI- NAVGOUT, directly maximizes the diversity score through the output distributions of each batch; the second model, Label Fine-Tuning (LFT), prepends to the source sequence a label continuously scaled by the diversity score to control the diversity level; the third model, RL, adopts Reinforcement Learning and treats the diversity score as a reward signal. Moreover, we experiment with a hybrid model by combining the loss terms of MINAVGOUT and RL. All four models outperform their base LSTM-RNN model on both diversity and relevance by a large margin, and are comparable to or better than competitive baselines (also verified via human evaluation). Moreover, our approaches are orthogonal to the base model, making them applicable as an add-on to other emerging better dialogue models in the future.

PDF Details

IJCAI Conference 2020 Conference Paper

Diagnosing the Environment Bias in Vision-and-Language Navigation

  • Yubo Zhang
  • Hao Tan
  • Mohit Bansal

Vision-and-Language Navigation (VLN) requires an agent to follow natural-language instructions, explore the given environments, and reach the desired target locations. These step-by-step navigational instructions are crucial when the agent is navigating new environments about which it has no prior knowledge. Most recent works that study VLN observe a significant performance drop when tested on unseen environments (i. e. , environments not used in training), indicating that the neural agent models are highly biased towards training environments. Although this issue is considered as one of the major challenges in VLN research, it is still under-studied and needs a clearer explanation. In this work, we design novel diagnosis experiments via environment re-splitting and feature replacement, looking into possible reasons for this environment bias. We observe that neither the language nor the underlying navigational graph, but the low-level visual appearance conveyed by ResNet features directly affects the agent model and contributes to this environment bias in results. According to this observation, we explore several kinds of semantic representations that contain less low-level visual information, hence the agent learned with these features could be better generalized to unseen testing environments. Without modifying the baseline agent model and its training method, our explored semantic features significantly decrease the performance gaps between seen and unseen on multiple datasets (i. e. R2R, R4R, and CVDN) and achieve competitive unseen results to previous state-of-the-art models.

PDF Details DOI

ICRA Conference 2020 Conference Paper

Enabling Robots to Understand Incomplete Natural Language Instructions Using Commonsense Reasoning

  • Haonan Chen
  • Hao Tan 0002
  • Alan Kuntz
  • Mohit Bansal
  • Ron Alterovitz

Enabling robots to understand instructions provided via spoken natural language would facilitate interaction between robots and people in a variety of settings in homes and workplaces. However, natural language instructions are often missing information that would be obvious to a human based on environmental context and common sense, and hence does not need to be explicitly stated. In this paper, we introduce Language-Model-based Commonsense Reasoning (LMCR), a new method which enables a robot to listen to a natural language instruction from a human, observe the environment around it, and automatically fill in information missing from the instruction using environmental context and a new commonsense reasoning approach. Our approach first converts an instruction provided as unconstrained natural language into a form that a robot can understand by parsing it into verb frames. Our approach then fills in missing information in the instruction by observing objects in its vicinity and leveraging commonsense reasoning. To learn commonsense reasoning automatically, our approach distills knowledge from large unstructured textual corpora by training a language model. Our results show the feasibility of a robot learning commonsense knowledge automatically from web-based textual corpora, and the power of learned commonsense reasoning models in enabling a robot to autonomously perform tasks based on incomplete natural language instructions.

Details

AAAI Conference 2020 Conference Paper

ManyModalQA: Modality Disambiguation and QA over Diverse Inputs

  • Darryl Hannan
  • Akshay Jain
  • Mohit Bansal

We present a new multimodal question answering challenge, MANYMODALQA, in which an agent must answer a question by considering three distinct modalities: text, images, and tables. We collect our data by scraping Wikipedia and then utilize crowdsourcing to collect question-answer pairs. Our questions are ambiguous, in that the modality that contains the answer is not easily determined based solely upon the question. To demonstrate this ambiguity, we construct a modality selector (or disambiguator) network, and this model gets substantially lower accuracy on our challenge set, compared to existing datasets, indicating that our questions are more ambiguous. By analyzing this model, we investigate which words in the question are indicative of the modality. Next, we construct a simple baseline MANYMODALQA model, which, based on the prediction from the modality selector, fires a corresponding pre-trained state-of-the-art unimodal QA model. We focus on providing the community with a new manymodal evaluation set and only provide a fine-tuning set, with the expectation that existing datasets and approaches will be transferred for most of the training, to encourage low-resource generalization without large, monolithic training sets for each new task. There is a significant gap between our baseline models and human performance; therefore, we hope that this challenge encourages research in end-to-end modality disambiguation and multimodal QA models, as well as transfer learning.

PDF Details

AAAI Conference 2020 Conference Paper

Modality-Balanced Models for Visual Dialogue

  • Hyounghun Kim
  • Hao Tan
  • Mohit Bansal

The Visual Dialog task requires a model to exploit both image and conversational context information to generate the next response to the dialogue. However, via manual analysis, we find that a large number of conversational questions can be answered by only looking at the image without any access to the context history, while others still need the conversation context to predict the correct answers. We demonstrate that due to this reason, previous joint-modality (history and image) models over-rely on and are more prone to memorizing the dialogue history (e. g. , by extracting certain keywords or patterns in the context information), whereas image-only models are more generalizable (because they cannot memorize or extract keywords from history) and perform substantially better at the primary normalized discounted cumulative gain (NDCG) task metric which allows multiple correct answers. Hence, this observation encourages us to explicitly maintain two models, i. e. , an image-only model and an image-history joint model, and combine their complementary abilities for a more balanced multimodal model. We present multiple methods for this integration of the two models, via ensemble and consensus dropout fusion with shared parameters. Empirically, our models achieve strong results on the Visual Dialog challenge 2019 (rank 3 on NDCG and high balance across metrics), and substantially outperform the winner of the Visual Dialog challenge 2018 on most metrics.

PDF Details

AAAI Conference 2020 Conference Paper

Multi-Source Domain Adaptation for Text Classification via DistanceNet-Bandits

  • Han Guo
  • Ramakanth Pasunuru
  • Mohit Bansal

Domain adaptation performance of a learning algorithm on a target domain is a function of its source domain error and a divergence measure between the data distribution of these two domains. We present a study of various distance-based measures in the context of NLP tasks, that characterize the dissimilarity between domains based on sample estimates. We first conduct analysis experiments to show which of these distance measures can best differentiate samples from same versus different domains, and are correlated with empirical results. Next, we develop a DistanceNet model which uses these distance measures, or a mixture of these distance measures, as an additional loss function to be minimized jointly with the task’s loss function, so as to achieve better unsupervised domain adaptation. Finally, we extend this model to a novel DistanceNet-Bandit model, which employs a multiarmed bandit controller to dynamically switch between multiple source domains and allow the model to learn an optimal trajectory and mixture of domains for transfer to the lowresource target domain. We conduct experiments on popular sentiment analysis datasets with several diverse domains and show that our DistanceNet model, as well as its dynamic bandit variant, can outperform competitive baselines in the context of unsupervised domain adaptation.

PDF Details

AAAI Conference 2019 Conference Paper

Analyzing Compositionality-Sensitivity of NLI Models

  • Yixin Nie
  • Yicheng Wang
  • Mohit Bansal

Success in natural language inference (NLI) should require a model to understand both lexical and compositional semantics. However, through adversarial evaluation, we find that several state-of-the-art models with diverse architectures are over-relying on the former and fail to use the latter. Further, this compositionality unawareness is not reflected via standard evaluation on current datasets. We show that removing RNNs in existing models or shuffling input words during training does not induce large performance loss despite the explicit removal of compositional information. Therefore, we propose a compositionality-sensitivity testing setup that analyzes models on natural examples from existing datasets that cannot be solved via lexical features alone (i. e. , on which a bag-of-words model gives a high probability to one wrong label), hence revealing the models’ actual compositionality awareness. We show that this setup not only highlights the limited compositional ability of current NLI models, but also differentiates model performance based on design, e. g. , separating shallow bag-of-words models from deeper, linguistically-grounded tree-based models. Our evaluation setup is an important analysis tool: complementing currently existing adversarial and linguistically driven diagnostic evaluations, and exposing opportunities for future work on evaluating models’ compositional understanding.

PDF Details

AAAI Conference 2019 Conference Paper

Combining Fact Extraction and Verification with Neural Semantic Matching Networks

  • Yixin Nie
  • Haonan Chen
  • Mohit Bansal

The increasing concern with misinformation has stimulated research efforts on automatic fact checking. The recentlyreleased FEVER dataset introduced a benchmark factverification task in which a system is asked to verify a claim using evidential sentences from Wikipedia documents. In this paper, we present a connected system consisting of three homogeneous neural semantic matching models that conduct document retrieval, sentence selection, and claim verification jointly for fact extraction and verification. For evidence retrieval (document retrieval and sentence selection), unlike traditional vector space IR models in which queries and sources are matched in some pre-designed term vector space, we develop neural models to perform deep semantic matching from raw textual input, assuming no intermediate term representation and no access to structured external knowledge bases. We also show that Pageview frequency can also help improve the performance of evidence retrieval results, that later can be matched by using our neural semantic matching network. For claim verification, unlike previous approaches that simply feed upstream retrieved evidence and the claim to a natural language inference (NLI) model, we further enhance the NLI model by providing it with internal semantic relatedness scores (hence integrating it with the evidence retrieval modules) and ontological WordNet features. Experiments on the FEVER dataset indicate that (1) our neural semantic matching method outperforms popular TF-IDF and encoder models, by significant margins on all evidence retrieval metrics, (2) the additional relatedness score and WordNet features improve the NLI model via better semantic awareness, and (3) by formalizing all three subtasks as a similar semantic matching problem and improving on all three stages, the complete model is able to achieve the state-of-the-art results on the FEVER test set (two times greater than baseline results). 1

PDF Details

ICRA Conference 2019 Conference Paper

Efficient Generation of Motion Plans from Attribute-Based Natural Language Instructions Using Dynamic Constraint Mapping

  • Jae Sung Park
  • Biao Jia
  • Mohit Bansal
  • Dinesh Manocha

We present an algorithm for combining natural language processing (NLP) and fast robot motion planning to automatically generate robot movements. Our formulation uses a novel concept called Dynamic Constraint Mapping to transform complex, attribute-based natural language instructions into appropriate cost functions and parametric constraints for optimization-based motion planning. We generate a factor graph from natural language instructions called the Dynamic Grounding Graph (DGG), which takes latent parameters into account. The coefficients of this factor graph are learned based on conditional random fields (CRFs) and are used to dynamically generate the constraints for motion planning. We map the cost function directly to the motion parameters of the planner and compute smooth trajectories in dynamic scenes. We highlight the performance of our approach in a simulated environment and via a human interacting with a 7-DOF Fetch robot using intricate language commands including negation, orientation specification, and distance constraints.

Details

AAAI Conference 2018 Conference Paper

Source-Target Inference Models for Spatial Instruction Understanding

  • Hao Tan
  • Mohit Bansal

Models that can execute natural language instructions for situated robotic tasks such as assembly and navigation have several useful applications in homes, offices, and remote scenarios. We study the semantics of spatially-referred configuration and arrangement instructions, based on the challenging Bisk-2016 blank-labeled block dataset. This task involves finding a source block and moving it to the target position (mentioned via a reference block and offset), where the blocks have no names or colors and are just referred to via spatial location features. We present novel models for the subtasks of source block classification and target position regression, based on joint-loss language and spatial-world representation learning, as well as CNN-based and dual attention models to compute the alignment between the world blocks and the instruction phrases. For target position prediction, we compare two inference approaches: annealed sampling via policy gradient versus expectation inference via supervised regression. Our models achieve the new state-of-the-art on this task, with an improvement of 47% on source block accuracy and 22% on target position distance.

PDF Details

AAAI Conference 2017 Conference Paper

Coherent Dialogue with Attention-Based Language Models

  • Hongyuan Mei
  • Mohit Bansal
  • Matthew Walter

We model coherent conversation continuation via RNNbased dialogue models equipped with a dynamic attention mechanism. Our attention-RNN language model dynamically increases the scope of attention on the history as the conversation continues, as opposed to standard attention (or alignment) models with a fixed input scope in a sequence-tosequence model. This allows each generated word to be associated with the most relevant words in its corresponding conversation history. We evaluate the model on two popular dialogue datasets, the open-domain MovieTriples dataset and the closed-domain Ubuntu Troubleshoot dataset, and achieve significant improvements over the state-of-the-art and baselines on several metrics, including complementary diversity-based metrics, human evaluation, and qualitative visualizations. We also show that a vanilla RNN with dynamic attention outperforms more complex memory models (e. g. , LSTM and GRU) by allowing for flexible, long-distance memory. We promote further coherence via topic modeling-based reranking.

PDF Details

AAAI Conference 2017 Conference Paper

Contextual RNN-GANs for Abstract Reasoning Diagram Generation

  • Viveka Kulharia
  • Arnab Ghosh
  • Amitabha Mukerjee
  • Vinay Namboodiri
  • Mohit Bansal

Understanding, predicting, and generating object motions and transformations is a core problem in artificial intelligence. Modeling sequences of evolving images may provide better representations and models of motion and may ultimately be used for forecasting, simulation, or video generation. Diagrammatic Abstract Reasoning is an avenue in which diagrams evolve in complex patterns and one needs to infer the underlying pattern sequence and generate the next image in the sequence. For this, we develop a novel Contextual Generative Adversarial Network based on Recurrent Neural Networks (Context-RNN-GANs), where both the generator and the discriminator modules are based on contextual history (modeled as RNNs) and the adversarial discriminator guides the generator to produce realistic images for the particular time step in the image sequence. We evaluate the Context-RNN-GAN model (and its variants) on a novel dataset of Diagrammatic Abstract Reasoning, where it performs competitively with 10th-grade human performance but there is still scope for interesting improvements as compared to college-grade human performance. We also evaluate our model on a standard video next-frame prediction task, achieving improved performance over comparable state-of-the-art.

PDF Details

AAAI Conference 2016 Conference Paper

Listen, Attend, and Walk: Neural Mapping of Navigational Instructions to Action Sequences

  • Hongyuan Mei
  • Mohit Bansal
  • Matthew Walter

We propose a neural sequence-to-sequence model for direction following, a task that is essential to realizing effective autonomous agents. Our alignment-based encoder-decoder model with long short-term memory recurrent neural networks (LSTM-RNN) translates natural language instructions to action sequences based upon a representation of the observable world state. We introduce a multi-level aligner that empowers our model to focus on sentence “regions” salient to the current world state by using multiple abstractions of the input sentence. In contrast to existing methods, our model uses no specialized linguistic resources (e. g. , parsers) or taskspecific annotations (e. g. , seed lexicons). It is therefore generalizable, yet still achieves the best results reported to-date on a benchmark single-sentence dataset and competitive results for the limited-training multi-sentence setting. We analyze our model through a series of ablations that elucidate the contributions of the primary components of our model.

PDF Details

ICLR Conference 2016 Conference Paper

Towards Universal Paraphrastic Sentence Embeddings

  • John Wieting
  • Mohit Bansal
  • Kevin Gimpel
  • Karen Livescu

We consider the problem of learning general-purpose, paraphrastic sentence embeddings based on supervision from the Paraphrase Database (Ganitkevitch et al., 2013). We compare six compositional architectures, evaluating them on annotated textual similarity datasets drawn both from the same distribution as the training data and from a wide range of other domains. We find that the most complex architectures, such as long short-term memory (LSTM) recurrent neural networks, perform best on the in-domain data. However, in out-of-domain scenarios, simple architectures such as word averaging vastly outperform LSTMs. Our simplest averaging model is even competitive with systems tuned for the particular tasks while also being extremely efficient and easy to use. In order to better understand how these architectures compare, we conduct further experiments on three supervised NLP tasks: sentence similarity, entailment, and sentiment classification. We again find that the word averaging models perform well for sentence similarity and entailment, outperforming LSTMs. However, on sentiment classification, we find that the LSTM performs very strongly-even recording new state-of-the-art performance on the Stanford Sentiment Treebank. We then demonstrate how to combine our pretrained sentence embeddings with these supervised tasks, using them both as a prior and as a black box feature extractor. This leads to performance rivaling the state of the art on the SICK similarity and entailment tasks. We release all of our resources to the research community with the hope that they can serve as the new baseline for further work on universal sentence embeddings.

Details