Author name cluster

Wenhu Chen

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.

47 papers

2 author rows

TMLR Journal 2026 Journal Article

BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actions

Tao Yu
Zhengbo Zhang
Zhiheng Lyu
Junhao Gong
Hongzhu Yi
Xinming Wang
Yuxuan Zhou
Jiabing Yang

Efficiently solving real-world problems with LLMs increasingly hinges on their ability to interact with dynamic web environments and autonomously acquire external information. While recent research like Search-R1 and WebDancer demonstrates strong performance in solving web tasks, they heavily rely on additional tools to convert the interactive web environment into static text content. This is in contrast to human browsing behaviors, which involve diverse interactions with the browser, such as scrolling, clicking, and typing. In this paper, we propose BrowserAgent, a more interactive agent that solves complex tasks through human-inspired browser actions. BrowserAgent operates directly on raw web pages via Playwright through a set of predefined browser actions. We adopt a two-stage training (Supervised Fine-Tuning (SFT) and Rejection Fine-Tuning (RFT)) to improve the model's generalization abilities. Despite using significantly less training data than Search-R1, BrowserAgent achieves more competitive results across different Open-QA tasks. Additionally, we introduce an explicit memory mechanism to store key conclusions across steps, further enhancing the model's reasoning capabilities for long-horizon tasks. Notably, BrowserAgent-7B can achieve around 20\% improvement over Search-R1 on multi-hop QA tasks like HotpotQA, 2Wiki, and Bamboogle. These results indicate that BrowserAgent can serve as a more advanced framework for more interactive and scalable web agents.

TMLR Journal 2026 Journal Article

QuickVideo: Real-Time Long Video Understanding with System Algorithm Co-Design

Benjamin Schneider
Dongfu Jiang
Chao Du
Tianyu Pang
Wenhu Chen

Long video understanding has emerged as a crucial capability in real-world applications such as meeting summarization, video surveillance, educational lecture analysis, and content moderation. However, it remains computationally prohibitive for VideoLLMs, primarily due to two bottlenecks: 1) sequential video decoding, the process of converting the raw bit stream to RGB frames can take up to a minute for hour-long video inputs, and 2) costly prefilling of up to several million tokens for LLM inference, resulting in high latency and memory use. To address these challenges, we propose QuickVideo, a system-algorithm co-design that substantially accelerates long video understanding to support real-time downstream applications. It comprises three key innovations: QuickCodec, a parallelized CPU-based video decoder that achieves 2–3× speedup by splitting videos into keyframe-aligned intervals processed concurrently. QuickPrefill, a memory-efficient prefilling method using KV-cache pruning to support more frames with less GPU memory; and an overlapping scheme that overlaps CPU video decoding with GPU inference. Together, these components reduce the time required to process a long video input by a minute, enabling fast, efficient video understanding even on limited hardware. Experiments show that QuickVideo generalizes across durations and sampling rates, making long video processing feasible in practice.

TMLR Journal 2026 Journal Article

StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs

Jialin Yang
Dongfu Jiang
Tony He
Sherman Siu
Yuxuan Zhang
Disen Liao
Zhuofeng Li
Huaye Zeng

As Large Language Models (LLMs) become integral to software development workflows, their ability to generate structured outputs has become critically important. We introduce $\textbf{StructEval}$, a comprehensive benchmark for evaluating LLMs' capabilities in producing both non-renderable (JSON, YAML, CSV) and renderable (HTML, React, SVG) structured formats. Unlike prior benchmarks, StructEval systematically evaluates structural fidelity across diverse formats through two paradigms: $\textbf{1)}$ generation tasks, producing structured output from natural language prompts, and $\textbf{2)}$ conversion tasks, translating between structured formats. Our benchmark encompasses 18 formats and 44 types of task, with novel metrics for format adherence and structural correctness. Results reveal significant performance gaps—even state-of-the-art models like o1-mini achieve only $75.58$ average score, with open-source alternatives lagging approximately $10$ points behind. We find generation tasks more challenging than conversion tasks, and producing correct visual content more difficult than generating text-only structures.

TMLR Journal 2026 Journal Article

VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents

Rui Meng
Ziyan Jiang
Ye Liu
Mingyi Su
Xinyi Yang
Yuepeng Fu
Can Qin
Raghuveer Thirukovalluru

Multimodal embedding models have been crucial in enabling various downstream tasks such as semantic similarity, information retrieval, and clustering over different modalities. However, existing multimodal embeddings like VLM2Vec, E5-V, GME are predominantly focused on natural images, with limited support for other visual forms such as videos and visual documents. This restricts their applicability in real-world scenarios, including AI agents, retrieval-augmented generation (RAG) systems, and recommendation. To close this gap, we propose VLM2Vec-V2, a unified framework for learning embeddings across diverse visual forms. First, we introduce MMEB-V2, a comprehensive benchmark that extends MMEB with five new task types: visual document retrieval, video retrieval, temporal grounding, video classification and video question answering -- spanning text, image, video, and visual document inputs. Next, we train VLM2Vec-V2, a general-purpose embedding model that supports text, image, video, and visual document inputs. Extensive experiments show that VLM2Vec-V2 achieves strong performance not only on the newly introduced video and document retrieval tasks, but also improves over prior baselines on the original image benchmarks. Through extensive evaluation, our study offers insights into the generalizability of various multimodal embedding models and highlights effective strategies for unified embedding learning, laying the groundwork for more scalable and adaptable representation learning in both research and real-world settings.

TMLR Journal 2025 Journal Article

ABC: Achieving Better Control of Visual Embeddings using VLLMs

Benjamin Schneider
Florian Kerschbaum
Wenhu Chen

Visual embedding models excel at zero-shot tasks like visual retrieval and classification. However, these models cannot be used for tasks that contain ambiguity or require user in- struction. These tasks necessitate an embedding model which outputs can use a natural language instruction to control the representation of a visual embedding. Existing CLIP- based approaches embed images and text independently, and fuse the result. We find that this results in weak interactions between modalities, and poor user control over the repre- sentation. We introduce ABC, an open-source multimodal embedding model that uses a vision-language model backbone to deeply integrate image features with natural language instructions. ABC achieves best-for-size performance on MSCOCO image-to-text retrieval and is the top performing model on classification and VQA tasks in the Massive Multimodal Embedding Benchmark. With a strongly unified vision-language representation, ABC can use natural language to solve subtle and potentially ambiguous visual retrieval problems. To evaluate this capability, we design CtrlBench, a benchmark that requires interleaving tex- tual instructions with image content for correct retrieval. ABC advances the state of visual embeddings, outputting high-quality visual representations with natural language control. Our model and datasets are available at our project page: https://tiger-ai-lab.github.io/ABC/

NeurIPS Conference 2025 Conference Paper

Breaking the Batch Barrier (B3) of Contrastive Learning via Smart Batch Mining

Raghuveer Thirukovalluru
Rui Meng
Ye Liu
Karthikeyan K
Mingyi Su
Ping Nie
Semih Yavuz
Yingbo Zhou

Contrastive learning (CL) is a prevalent technique for training embedding models, which pulls semantically similar examples (positives) closer in the representation space while pushing dissimilar ones (negatives) further apart. A key source of negatives are "in-batch" examples, i. e. , positives from other examples in the batch. Effectiveness of such models is hence strongly influenced by the size and quality of training batches. In this work, we propose Breaking the Batch Barrier (B3), a novel batch construction strategy designed to curate high-quality batches for CL. Our approach begins by using a pretrained teacher embedding model to rank all examples in the dataset, from which a sparse similarity graph is constructed. A community detection algorithm is then applied to this graph to identify clusters of examples that serve as strong negatives for one another. The clusters are then used to construct batches that are rich in in-batch negatives. Empirical results on the MMEB multimodal embedding benchmark (36 tasks) demonstrate that our method sets a new state of the art, outperforming previous best methods by +1. 3 and +2. 9 points at the 7B and 2B model scales, respectively. Notably, models trained with B3 surpass existing state-of-the-art results even with a batch size as small as 64, which is 4–16× smaller than that required by other methods. Moreover, experiments show that B3 generalizes well across domains and tasks, maintaining strong performance even when trained with considerably weaker teachers.

NeurIPS Conference 2025 Conference Paper

General-Reasoner: Advancing LLM Reasoning Across All Domains

Xueguang Ma
Qian Liu
Dongfu Jiang
Ge Zhang
Zejun Ma
Wenhu Chen

Reinforcement learning (RL) has recently demonstrated strong potential in enhancing the reasoning capabilities of large language models (LLMs). Particularly, the "Zero" reinforcement learning introduced by Deepseek-R1-Zero, enables direct RL training of base LLMs without relying on an intermediate supervised fine-tuning stage. Despite these advancements, current works for LLM reasoning mainly focus on mathematical and coding domains, largely due to data abundance and the ease of answer verification. This limits the applicability and generalization of such models to broader domains, where questions often have diverse answer representations, and data is more scarce. In this paper, we propose General-Reasoner, a novel training framework designed to enhance LLM reasoning capabilities across diverse domains. Our key contributions include: (1) constructing a large-scale, high-quality dataset of questions with verifiable answers curated by web crawling, covering a wide range of disciplines; and (2) developing a generative model-based answer verifier, which replaces traditional rule-based verification with the capability of chain-of-thought and context-awareness. We train a series of models and evaluate them on a wide range of datasets covering wide domains like physics, chemistry, finance, electronics etc. Our comprehensive evaluation across these 12 benchmarks (e. g. MMLU-Pro, GPQA, SuperGPQA, TheoremQA, BBEH and MATH AMC) demonstrates that General-Reasoner outperforms existing baseline methods, achieving robust and generalizable reasoning performance while maintaining superior effectiveness in mathematical reasoning tasks.

ICLR Conference 2025 Conference Paper

Harnessing Webpage UIs for Text-Rich Visual Understanding

Junpeng Liu 0001
Tianyue Ou
Yifan Song 0002
Yuxiao Qu
Wai Lam
Chenyan Xiong
Wenhu Chen
Graham Neubig

Text-rich visual understanding—the ability to interpret both textual content and visual elements within a scene—is crucial for multimodal large language models (MLLMs) to effectively interact with structured environments. We propose leveraging webpage UIs as a naturally structured and diverse data source to enhance MLLMs’ capabilities in this area. Existing approaches, such as rule-based extraction, multimodal model captioning, and rigid HTML parsing, are hindered by issues like noise, hallucinations, and limited generalization. To overcome these challenges, we introduce MultiUI, a dataset of 7.3 million samples spanning various UI types and tasks, structured using enhanced accessibility trees and task taxonomies. By scaling multimodal instructions from web UIs through LLMs, our dataset enhances generalization beyond web domains, significantly improving performance in document understanding, GUI comprehension, grounding, and advanced agent tasks. This demonstrates the potential of structured web data to elevate MLLMs’ proficiency in processing text-rich visual environments and generalizing across domains.

TMLR Journal 2025 Journal Article

Long-context LLMs Struggle with Long In-context Learning

Tianle Li
Ge Zhang
Quy Duc Do
Xiang Yue
Wenhu Chen

Large Language Models (LLMs) have made significant strides in handling long sequences. Some models like Gemini could even be capable of dealing with millions of tokens. However, their performance evaluation has largely been confined to metrics like perplexity and synthetic tasks, which may not fully capture their true abilities in more challenging, real-world scenarios. We introduce a benchmark (LongICLBench) for long in-context learning in extreme-label classification using six datasets with 28 to 174 classes and input lengths from 2K to 50K tokens. Our benchmark requires LLMs to comprehend the entire input to recognize the massive label spaces to make correct predictions. We evaluate on 15 long-context LLMs and find that they perform well on less challenging classification tasks with smaller label space and shorter demonstrations. However, they struggle with more challenging task like Discovery with 174 labels, suggesting a gap in their ability to process long, context-rich sequences. Further analysis reveals a bias towards labels presented later in the sequence and a need for improved reasoning over multiple pieces of information. Our study reveals that long context understanding and reasoning is still a challenging task for the existing LLMs. We believe LongICLBench could serve as a more realistic evaluation for the future long-context LLMs.

ICLR Conference 2025 Conference Paper

MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks

Jiacheng Chen
Tianhao Liang
Sherman Siu
Zhengqing Wang
Kai Wang 0068
Yubo Wang 0019
Yuansheng Ni
Ziyan Jiang

We present MEGA-Bench, an evaluation suite that scales multimodal evaluation to over 500 real-world tasks, to address the highly heterogeneous daily use cases of end users. Our objective is to optimize for a set of high-quality data samples that cover a highly diverse and rich set of multimodal tasks, while enabling cost-effective and accurate model evaluation. In particular, we collected 505 realistic tasks encompassing over 8,000 samples from 16 expert annotators to extensively cover the multimodal task space. Instead of unifying these problems into standard multi-choice questions (like MMMU, MM-Bench, and MMT-Bench), we embrace a wide range of output formats like numbers, phrases, code, \LaTeX, coordinates, JSON, free-form, etc. To accommodate these formats, we developed over 40 metrics to evaluate these tasks. Unlike existing benchmarks, MEGA-Bench offers a fine-grained capability report across multiple dimensions (e.g., application, input type, output format, skill), allowing users to interact with and visualize model capabilities in depth. We evaluate a wide variety of frontier vision-language models on MEGA-Bench to understand their capabilities across these dimensions.

NeurIPS Conference 2025 Conference Paper

MoCha: Towards Movie-Grade Talking Character Generation

Cong Wei
Bo Sun
Haoyu Ma
Ji Hou
Felix Juefei-Xu
Zecheng He
Xiaoliang Dai
Luxin Zhang

Recent advancements in video generation have achieved impressive motion realism, yet they often overlook character-driven storytelling, a crucial task for automated film, animation generation. We introduce Talking Characters, a more realistic task to generate talking character animations directly from speech and text. Unlike talking head tasks, Talking Characters aims at generating the full portrait of one or more characters beyond the facial region. In this paper, we propose MoCha, the first of its kind to generate talking characters. To ensure precise synchronization between video and speech, we propose a localized audio attention mechanism that effectively aligns speech and video tokens. To address the scarcity of large-scale speech-labelled video datasets, we introduce a joint training strategy that leverages both speech-labelled and text-labelled video data, significantly improving generalization across diverse character actions. We also design structured prompt templates with character tags, enabling, for the first time, multi-character conversation with turn-based dialogue—allowing AI-generated characters to engage in context-aware conversations with cinematic coherence. Extensive qualitative and quantitative evaluations, including human evaluation studies and benchmark comparisons, demonstrate that MoCha sets a new standard for AI-generated cinematic storytelling, achieving superior realism, controllability and generalization.

ICLR Conference 2025 Conference Paper

OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision

Cong Wei 0001
Zheyang Xiong
Weiming Ren
Xeron Du
Ge Zhang 0009
Wenhu Chen

Instruction-guided image editing methods have demonstrated significant potential by training diffusion models on automatically synthesized or manually annotated image editing pairs. However, these methods remain far from practical, real-life applications. We identify three primary challenges contributing to this gap. Firstly, existing models have limited editing skills due to the biased synthesis process. Secondly, these methods are trained with datasets with a high volume of noise and artifacts. This is due to the application of simple filtering methods like CLIP-score. Thirdly, all these datasets are restricted to a single low resolution and fixed aspect ratio, limiting the versatility to handle real-world use cases. In this paper, we present OmniEdit, which is an omnipotent editor to handle seven different image editing tasks with any aspect ratio seamlessly. Our contribution is in four folds: (1) OmniEdit is trained by utilizing the supervision from seven different specialist models to ensure task coverage. (2) we utilize importance sampling based on the scores provided by large multimodal models (like GPT-4o) instead of CLIP-score to improve the data quality. (3) we propose a new editing architecture called EditNet to greatly boost the editing success rate, (4) we provide images with different aspect ratios to ensure that our model can handle any image in the wild. We have curated a test set containing images of different aspect ratios, accompanied by diverse instructions to cover different tasks. Both automatic evaluation and human evaluations demonstrate that OmniEdit can significantly outperforms all the existing models.

NeurIPS Conference 2025 Conference Paper

Pixel Reasoner: Incentivizing Pixel Space Reasoning via Curiosity-Driven Reinforcement Learning

Alex Su
Haozhe Wang
Weiming Ren
Fangzhen Lin
Wenhu Chen

Chain-of-thought reasoning has significantly improved the performance of Large Language Models (LLMs) across various domains. However, this reasoning process has been confined exclusively to textual space, limiting its effectiveness in visually intensive tasks. To address this limitation, we introduce the concept of pixel-space reasoning. Within this novel framework, Vision-Language Models (VLMs) are equipped with a suite of visual reasoning operations, such as zoom-in and select-frame. These operations enable VLMs to directly inspect, interrogate, and infer from visual evidences, thereby enhancing reasoning fidelity for visual tasks. Cultivating such pixel-space reasoning capabilities in VLMs presents notable challenges, including the model’s initially imbalanced competence and its reluctance to adopt the newly introduced pixel-space operations. We address these challenges through a two-phase training approach. The first phase employs instruction tuning on synthesized reasoning traces to familiarize the model with the novel visual operations. Following this, a reinforcement learning (RL) phase leverages a curiosity-driven reward scheme to balance exploration between pixel-space reasoning and textual reasoning. With these visual operations, VLMs can interact with complex visual inputs, such as information-rich images or videos to proactively gather necessary information. We demonstrate that this approach significantly improves VLM performance across diverse visual reasoning benchmarks. Our 7B model, Pixel-Reasoner, achieves 84% on V* bench, 74% on TallyQA-Complex, and 84% on InfographicsVQA, marking the highest accuracy achieved by any open-source model to date. These results highlight the importance of pixel-space reasoning and the effectiveness of our framework.

TMLR Journal 2025 Journal Article

PixelWorld: Towards Perceiving Everything as Pixels

Zhiheng Lyu
Xueguang Ma
Wenhu Chen

Recent agentic language models increasingly accept raw camera pixels rather than tokenized text, underscoring the need for a unified perception paradigm. We explore this idea through Perceive Everything as Pixels (PEAP) and release PixelWorld, a benchmark that renders natural-language, tabular, mathematical and diagrammatic inputs into a single pixel space. Experiments show that PEAP attains competitive accuracy on semantic-understanding tasks, indicating that a vision transformer can capture global textual semantics without explicit tokens. In contrast, reasoning-intensive benchmarks (math and code) exhibit sharp performance drops; however, Chain-of-Thought prompting partially mitigates this gap, hinting that explicit reasoning traces compensate for the missing token structure. We also observe that scenarios with tightly intertwined visual--text cues benefit from the unified pixel view, reducing preprocessing overhead and ambiguity relative to split-modality baselines. PixelWorld therefore provides a compact yet challenging yardstick and encourages wider adoption of PEAP for holistic evaluation of next-generation vision–language agents.

ICLR Conference 2025 Conference Paper

T2V-Turbo-v2: Enhancing Video Model Post-Training through Data, Reward, and Conditional Guidance Design

Jiachen Li
Qian Long
Jian Zheng
Xiaofeng Gao 0002
Robinson Piramuthu
Wenhu Chen
William Yang Wang

In this paper, we focus on enhancing a diffusion-based text-to-video (T2V) model during the post-training phase by distilling a highly capable consistency model from a pretrained T2V model. Our proposed method, T2V-Turbo-v2, introduces a significant advancement by integrating various supervision signals, including high-quality training data, reward model feedback, and conditional guidance, into the consistency distillation process. Through comprehensive ablation studies, we highlight the crucial importance of tailoring datasets to specific learning objectives and the effectiveness of learning from diverse reward models for enhancing both the visual quality and text-video alignment. Additionally, we highlight the vast design space of conditional guidance strategies, which centers on designing an effective energy function to augment the teacher ODE solver. We demonstrate the potential of this approach by extracting motion guidance from the training datasets and incorporating it into the ODE solver, showcasing its effectiveness in improving the motion quality of the generated videos with the improved motion-related metrics from VBench and T2V-CompBench. Empirically, our T2V-Turbo-v2 establishes a new state-of-the-art result on VBench, **with a Total score of 85.13**, surpassing proprietary systems such as Gen-3 and Kling.

NeurIPS Conference 2025 Conference Paper

VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning

Haozhe Wang
Chao Qu
Zuming Huang
Wei Chu
Fangzhen Lin
Wenhu Chen

Recently, slow-thinking systems like GPT-o1 and DeepSeek-R1 have demonstrated great potential in solving challenging problems through explicit reflection. They significantly outperform the best fast-thinking models, such as GPT-4o, on various math and science benchmarks. However, their multimodal reasoning capabilities remain on par with fast-thinking models. For instance, GPT-o1's performance on benchmarks like MathVista, MathVerse, and MathVision is similar to fast-thinking models. In this paper, we aim to enhance the slow-thinking capabilities of vision-language models using reinforcement learning (without relying on distillation) to advance the state of the art. First, we adapt the GRPO algorithm with a novel technique called Selective Sample Replay (SSR) to address the vanishing advantages problem. While this approach yields strong performance, the resulting RL-trained models exhibit limited self-reflection or self-verification. To further encourage slow-thinking, we introduce Forced Rethinking, which appends a rethinking trigger token to the end of rollouts in RL training, explicitly enforcing a self-reflection reasoning step. By combining these two techniques, our model, VL-Rethinker, advances state-of-the-art scores on MathVista, MathVerse to achieve 80. 4%, 63. 5% respectively. VL-Rethinker also achieves open-source SoTA on multi-disciplinary benchmarks such as MathVision, MMMU-Pro, EMMA, and MEGA-Bench, narrowing the gap with OpenAI-o1. We conduct comprehensive ablations and analysis to provide insights into the effectiveness of our approach.

ICLR Conference 2025 Conference Paper

VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks

Ziyan Jiang
Rui Meng
Xinyi Yang 0002
Semih Yavuz
Yingbo Zhou 0002
Wenhu Chen

Embedding models play a crucial role in a variety of downstream tasks, including semantic similarity, information retrieval, and clustering. While there has been a surge of interest in developing universal text embedding models that generalize across tasks (e.g., MTEB), progress in learning universal multimodal embedding models has been comparatively slow, despite their importance and practical applications. In this work, we explore the potential of building universal multimodal embeddings capable of handling a broad range of downstream tasks. Our contributions are twofold: (1) we propose MMEB (Massive Multimodal Embedding Benchmark), which covers four meta-tasks (classification, visual question answering, multimodal retrieval, and visual grounding) and 36 datasets, including 20 training datasets and 16 evaluation datasets spanning both in-distribution and out-of-distribution tasks, and (2) VLM2Vec (Vision-Language Model → Vector), a contrastive training framework that transforms any vision-language model into an embedding model through contrastive training on MMEB. Unlike previous models such as CLIP and BLIP, which encode text and images independently without task-specific guidance, VLM2Vec can process any combination of images and text while incorporating task instructions to generate a fixed-dimensional vector. We develop a series of VLM2Vec models based on state-of-the-art VLMs, including Phi-3.5-V, LLaVA-1.6, and Qwen2-VL, and evaluate them on MMEB’s benchmark. With LoRA tuning, VLM2Vec achieves a 10% to 20% improvement over existing multimodal embedding models on MMEB’s evaluation sets. Our findings reveal that VLMs are surprisingly strong embedding models.

TMLR Journal 2024 Journal Article

AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing Tasks

Max Ku
Cong Wei
Weiming Ren
Huan Yang
Wenhu Chen

In the dynamic field of digital content creation using generative models, state-of-the-art video editing models still do not offer the level of quality and control that users desire. Previous works on video editing either extended from image-based generative models in a zero-shot manner or necessitated extensive fine-tuning, which can hinder the production of fluid video edits. Furthermore, these methods frequently rely on textual input as the editing guidance, leading to ambiguities and limiting the types of edits they can perform. Recognizing these challenges, we introduce AnyV2V, a novel tuning-free paradigm designed to simplify video editing into two primary steps: (1) employing an off-the-shelf image editing model to modify the first frame, (2) utilizing an existing image-to-video generation model to generate the edited video through temporal feature injection. AnyV2V can leverage any existing image editing tools to support an extensive array of video editing tasks, including prompt-based editing, reference-based style transfer, subject-driven editing, and identity manipulation, which were unattainable by previous methods. AnyV2V can also support any video length. Our evaluation shows that AnyV2V achieved CLIP Scores comparable to other baseline methods. Furthermore, AnyV2V significantly outperformed these baselines in human evaluations, demonstrating notable improvements in visual consistency with the source video while producing high-quality edits across all editing tasks.

TMLR Journal 2024 Journal Article

ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation

Weiming Ren
Huan Yang
Ge Zhang
Cong Wei
Xinrun Du
Wenhao Huang
Wenhu Chen

Image-to-video (I2V) generation aims to use the initial frame (alongside a text prompt) to create a video sequence. A grand challenge in I2V generation is to maintain visual consistency throughout the video: existing methods often struggle to preserve the integrity of the subject, background, and style from the first frame, as well as ensure a fluid and logical progression within the video narrative. To mitigate these issues, we propose ConsistI2V, a diffusion-based method to enhance visual consistency for I2V generation. Specifically, we introduce (1) spatiotemporal attention over the first frame to maintain spatial and motion consistency, (2) noise initialization from the low-frequency band of the first frame to enhance layout consistency. These two approaches enable ConsistI2V to generate highly consistent videos. We also extend the proposed approaches to show their potential to improve consistency in auto-regressive long video generation and camera motion control. To verify the effectiveness of our method, we propose I2V-Bench, a comprehensive evaluation benchmark for I2V generation. Our automatic and human evaluation results demonstrate the superiority of ConsistI2V over existing methods.

NeurIPS Conference 2024 Conference Paper

GenAI Arena: An Open Evaluation Platform for Generative Models

Dongfu Jiang
Max Ku
Tianle Li
Yuansheng Ni
Shizhuo Sun
Rongqi Fan
Wenhu Chen

Generative AI has made remarkable strides to revolutionize fields such as image and video generation. These advancements are driven by innovative algorithms, architecture, and data. However, the rapid proliferation of generative models has highlighted a critical gap: the absence of trustworthy evaluation metrics. Current automatic assessments such as FID, CLIP, FVD, etc often fail to capture the nuanced quality and user satisfaction associated with generative outputs. This paper proposes an open platform GenAI-Arena to evaluate different image and video generative models, where users can actively participate in evaluating these models. By leveraging collective user feedback and votes, GenAI-Arena aims to provide a more democratic and accurate measure of model performance. It covers three tasks of text-to-image generation, text-to-video generation, and image editing respectively. Currently, we cover a total of 35 open-source generative models. GenAI-Arena has been operating for seven months, amassing over 9000 votes from the community. We describe our platform, analyze the data, and explain the statistical methods for ranking the models. To further promote the research in building model-based evaluation metrics, we release a cleaned version of our preference data for the three tasks, namely GenAI-Bench. We prompt the existing multi-modal models like Gemini, and GPT-4o to mimic human voting. We compute the accuracy by comparing the model voting with the human voting to understand their judging abilities. Our results show existing multimodal models are still lagging in assessing the generated visual content, even the best model GPT-4o only achieves an average accuracy of $49. 19\%$ across the three generative tasks. Open-source MLLMs perform even worse due to the lack of instruction-following and reasoning ability in complex vision scenarios.

PDF Details DOI

ICLR Conference 2024 Conference Paper

ImagenHub: Standardizing the evaluation of conditional image generation models

Max Ku
Tianle Li
Kai Zhang 0033
Yujie Lu
Xingyu Fu
Wenwen Zhuang
Wenhu Chen

Recently, a myriad of conditional image generation and editing models have been developed to serve different downstream tasks, including text-to-image generation, text-guided image editing, subject-driven image generation, control-guided image generation, etc. However, we observe huge inconsistencies in experimental conditions: datasets, inference, and evaluation metrics -- render fair comparisons difficult. This paper proposes ImagenHub, which is a one-stop library to standardize the inference and evaluation of all the conditional image generation models. Firstly, we define seven prominent tasks and curate high-quality evaluation datasets for them. Secondly, we built a unified inference pipeline to ensure fair comparison. Thirdly, we design two human evaluation scores, i.e. Semantic Consistency and Perceptual Quality, along with comprehensive guidelines to evaluate generated images. We train expert raters to evaluate the model outputs based on the proposed metrics. Our human evaluation achieves a high inter-worker agreement of Krippendorff’s alpha on 76\% models with a value higher than 0.4. We comprehensively evaluated a total of around 30 models and observed three key takeaways: (1) the existing models’ performance is generally unsatisfying except for Text-guided Image Generation and Subject-driven Image Generation, with 74\% models achieving an overall score lower than 0.5. (2) we examined the claims from published papers and found 83\% of them hold with a few exceptions. (3) None of the existing automatic metrics has a Spearman's correlation higher than 0.2 except subject-driven image generation. Moving forward, we will continue our efforts to evaluate newly published models and update our leaderboard to keep track of the progress in conditional image generation.

ICLR Conference 2024 Conference Paper

Kosmos-G: Generating Images in Context with Multimodal Large Language Models

Xichen Pan
Li Dong 0004
Shaohan Huang
Zhiliang Peng
Wenhu Chen
Furu Wei

Recent advancements in subject-driven image generation have made significant strides. However, current methods still fall short in diverse application scenarios, as they require test-time tuning and cannot accept interleaved multi-image and text input. These limitations keep them far from the ultimate goal of "image as a foreign language in image generation." This paper presents Kosmos-G, a model that leverages the advanced multimodal perception capabilities of Multimodal Large Language Models (MLLMs) to tackle the aforementioned challenge. Our approach aligns the output space of MLLM with CLIP using the textual modality as an anchor and performs compositional instruction tuning on curated data. Kosmos-G demonstrates an impressive capability of zero-shot subject-driven generation with interleaved multi-image and text input. Notably, the score distillation instruction tuning requires no modifications to the image decoder. This allows for a seamless substitution of CLIP and effortless integration with a myriad of U-Net techniques ranging from fine-grained controls to personalized image decoder variants. We posit Kosmos-G as an initial attempt towards the goal of "image as a foreign language in image generation."

ICML Conference 2024 Conference Paper

MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions

Kai Zhang 0033
Yi Luan
Hexiang Hu
Kenton Lee
Siyuan Qiao
Wenhu Chen
Yu Su 0001
Ming-Wei Chang

Image retrieval, i. e. , finding desired images given a reference image, inherently encompasses rich, multi-faceted search intents that are difficult to capture solely using image-based measures. Recent works leverage text instructions to allow users to more freely express their search intents. However, they primarily focus on image pairs that are visually similar and/or can be characterized by a small set of pre-defined relations. The core thesis of this paper is that text instructions can enable retrieving images with richer relations beyond visual similarity. To show this, we introduce MagicLens, a series of self-supervised image retrieval models that support open-ended instructions. MagicLens is built on a key novel insight: image pairs that naturally occur on the same web pages contain a wide range of implicit relations (e. g. , inside view of), and we can bring those implicit relations explicit by synthesizing instructions via foundation models. Trained on 36. 7M (query image, instruction, target image) triplets with rich semantic relations mined from the web, MagicLens achieves results comparable with or better than prior best on eight benchmarks of various image retrieval tasks, while maintaining high parameter efficiency with a significantly smaller model size. Additional human analyses on a 1. 4M-image unseen corpus further demonstrate the diversity of search intents supported by MagicLens. Code and models are publicly available at the https: //open-vision-language. github. io/MagicLens/.

NeurIPS Conference 2024 Conference Paper

MAmmoTH2: Scaling Instructions from the Web

Xiang Yue
Tuney Zheng
Ge Zhang
Wenhu Chen

Instruction tuning improves the reasoning abilities of large language models (LLMs), with data quality and scalability being the crucial factors. Most instruction tuning data come from human crowd-sourcing or GPT-4 distillation. We propose a paradigm to efficiently harvest 10 million naturally existing instruction data from the pre-training web corpus to enhance LLM reasoning. Our approach involves (1) recalling relevant documents, (2) extracting instruction-response pairs, and (3) refining the extracted pairs using open-source LLMs. Fine-tuning base LLMs on this dataset, we build MAmmoTH2 models, which significantly boost performance on reasoning benchmarks. Notably, MAmmoTH2-7B’s (Mistral) performance increases from 11% to 36. 7% on MATH and from 36% to 68. 4% on GSM8K without training on any in-domain data. Further training MAmmoTH2 on public instruction tuning datasets yields MAmmoTH2-Plus, achieving state-of-the-art performance on several reasoning and chatbot benchmarks. Our work demonstrates how to harvest large-scale, high-quality instruction data without costly human annotation or GPT-4 distillation, providing a new paradigm for building better instruction tuning data.

PDF Details DOI

ICLR Conference 2024 Conference Paper

MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning

Xiang Yue
Xingwei Qu
Ge Zhang 0009
Yao Fu
Wenhao Huang 0001
Huan Sun 0001
Yu Su 0001
Wenhu Chen

We introduce MAmmoTH, a series of open-source large language models (LLMs) specifically tailored for general math problem-solving. The MAmmoTH models are trained on MathInstruct, our meticulously curated instruction tuning dataset. MathInstruct is compiled from 13 math datasets with intermediate rationales, six of which have rationales newly curated by us. It presents a unique hybrid of chain-of-thought (CoT) and program-of-thought (PoT) rationales, and also ensures extensive coverage of diverse fields in math. The hybrid of CoT and PoT not only unleashes the potential of tool use but also allows different thought processes for different math problems. As a result, the MAmmoTH series substantially outperform existing open-source models on nine mathematical reasoning datasets across all scales with an average accuracy gain between 16% and 32%. Remarkably, our MAmmoTH-7B model reaches 33% on MATH (a competition-level dataset), which exceeds the best open-source 7B model (WizardMath) by 23%, and the MAmmoTH-34B model achieves 44% accuracy on MATH, even surpassing GPT-4’s CoT result. Our work underscores the importance of diverse problem coverage and the use of hybrid rationales in developing superior math generalist models.

TMLR Journal 2024 Journal Article

Mantis: Interleaved Multi-Image Instruction Tuning

Dongfu Jiang
Xuan He
Huaye Zeng
Cong Wei
Max Ku
Qian Liu
Wenhu Chen

Large multimodal models (LMMs) have shown great results in single-image vision language tasks. However, their abilities to solve multi-image visual language tasks is yet to be improved. The existing LMMs like OpenFlamingo, Emu2, and Idefics gain their multi-image ability through pre-training on hundreds of millions of noisy interleaved image-text data from the web, which is neither efficient nor effective. In this paper, we aim to build strong multi-image LMMs via instruction tuning with academic-level resources. Therefore, we meticulously construct Mantis-Instruct containing 721K multi-image instruction data to train a family of Mantis models. The instruction tuning empowers Mantis with different multi-image skills like co-reference, comparison, reasoning, and temporal understanding. We evaluate Mantis on 8 multi-image benchmarks and 6 single-image benchmarks. Mantis-Idefics2 can achieve SoTA results on all the multi-image benchmarks and beat the strongest multi-image baseline, Idefics2-8B by an average of 13 absolute points. Notably, Idefics2-8B was pre-trained on 140M interleaved multi-image data, which is 200x larger than Mantis-Instruct. We observe that Mantis performs equivalently well on the held-in and held-out benchmarks, which shows its generalization ability. We further evaluate Mantis on single-image benchmarks and demonstrate that Mantis also maintains a strong single-image performance on par with CogVLM and Emu2. Our results show that multi-image abilities are not necessarily gained through massive pre-training, instead, they can be gained by low-cost instruction tuning. The training and evaluation of Mantis has paved the road for future work to improve LMMs' multi-image abilities.

ICLR Conference 2024 Conference Paper

MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training

Yizhi Li
Ruibin Yuan
Ge Zhang 0009
Yinghao Ma
Xingran Chen
Hanzhi Yin
Chenghao Xiao
Chenghua Lin 0002

Self-supervised learning (SSL) has recently emerged as a promising paradigm for training generalisable models on large-scale data in the fields of vision, text, and speech. Although SSL has been proven effective in speech and audio, its application to music audio has yet to be thoroughly explored. This is partially due to the distinctive challenges associated with modelling musical knowledge, particularly tonal and pitched characteristics of music. To address this research gap, we propose an acoustic **M**usic und**ER**standing model with large-scale self-supervised **T**raining (**MERT**), which incorporates teacher models to provide pseudo labels in the masked language modelling (MLM) style acoustic pre-training. In our exploration, we identified an effective combination of teacher models, which outperforms conventional speech and audio approaches in terms of performance. This combination includes an acoustic teacher based on Residual Vector Quantization - Variational AutoEncoder (RVQ-VAE) and a musical teacher based on the Constant-Q Transform (CQT). Furthermore, we explore a wide range of settings to overcome the instability in acoustic language model pre-training, which allows our designed paradigm to scale from 95M to 330M parameters. Experimental results indicate that our model can generalise and perform well on 14 music understanding tasks and attain state-of-the-art (SOTA) overall scores.

NeurIPS Conference 2024 Conference Paper

MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark

Yubo Wang
Xueguang Ma
Ge Zhang
Yuansheng Ni
Abhranil Chandra
Shiguang Guo
Weiming Ren
Aaran Arulraj

In the age of large-scale language models, benchmarks like the Massive Multitask Language Understanding (MMLU) have been pivotal in pushing the boundaries of what AI can achieve in language comprehension and reasoning across diverse domains. However, as models continue to improve, their performance on these benchmarks has begun to plateau, making it increasingly difficult to discern differences in model capabilities. This paper introduces MMLU-Pro, an enhanced dataset designed to extend the mostly knowledge-driven MMLU benchmark by integrating more challenging, reasoning-focused questions and expanding the choice set from four to ten options. Additionally, MMLU-Pro eliminates part of the trivial and noisy questions in MMLU. Our experimental results show that MMLU-Pro not only raises the challenge, causing a significant drop in accuracy by 16\% to 33\% compared to MMLU, but also demonstrates greater stability under varying prompts. With 24 different prompt styles tested, the sensitivity of model scores to prompt variations decreased from 4-5\% in MMLU to just 2\% in MMLU-Pro. Additionally, we found that models utilizing Chain of Thought (CoT) reasoning achieved better performance on MMLU-Pro compared to direct answering, which is in stark contrast to the findings on the original MMLU, indicating that MMLU-Pro includes more complex reasoning questions. Our assessments confirm that MMLU-Pro is more discriminative benchmark to better track progress in the field.

PDF Details DOI

TMLR Journal 2024 Journal Article

Reward Guided Latent Consistency Distillation

Jiachen Li
Weixi Feng
Wenhu Chen
William Yang Wang

Latent Consistency Distillation (LCD) has emerged as a promising paradigm for efficient text-to-image synthesis. By distilling a latent consistency model (LCM) from a pre-trained teacher latent diffusion model (LDM), LCD facilitates the generation of high-fidelity images within merely 2 to 4 inference steps. However, the LCM's efficient inference is obtained at the cost of the sample quality. In this paper, we propose compensating the quality loss by aligning LCM's output with human preference during training. Specifically, we introduce Reward Guided LCD (RG-LCD), which integrates feedback from a reward model (RM) into the LCD process by augmenting the original LCD loss with the objective of maximizing the reward associated with LCM's single-step generation. As validated through human evaluation, when trained with the feedback of a good RM, the 2-step generations from our RG-LCM are favored by humans over the 50-step DDIM samples from the teacher LDM, representing a 25-time inference acceleration without quality loss. As directly optimizing towards differentiable RMs can suffer from over-optimization, we take the initial step to overcome this difficulty by proposing the use of a latent proxy RM (LRM). This novel component serves as an intermediary, connecting our LCM with the RM. Empirically, we demonstrate that incorporating the LRM into our RG-LCD successfully avoids high-frequency noise in the generated images, contributing to both improved Fréchet Inception Distance (FID) on MS-COCO and a higher HPSv2.1 score on HPSv2's test set, surpassing those achieved by the baseline LCM. Project Page: https://rg-lcd.github.io/

NeurIPS Conference 2024 Conference Paper

T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback

Jiachen Li
Weixi Feng
Tsu-Jui Fu
Xinyi Wang
Sugato Basu
Wenhu Chen
William Y. Wang

Diffusion-based text-to-video (T2V) models have achieved significant success but continue to be hampered by the slow sampling speed of their iterative sampling processes. To address the challenge, consistency models have been proposed to facilitate fast inference, albeit at the cost of sample quality. In this work, we aim to break the quality bottleneck of a video consistency model (VCM) to achieve both fast and high-quality video generation. We introduce T2V-Turbo, which integrates feedback from a mixture of differentiable reward models into the consistency distillation (CD) process of a pre-trained T2V model. Notably, we directly optimize rewards associated with single-step generations that arise naturally from computing the CD loss, effectively bypassing the memory constraints imposed by backpropagating gradients through an iterative sampling process. Remarkably, the 4-step generations from our T2V-Turbo achieve the highest total score on VBench, even surpassing Gen-2 and Pika. We further conduct human evaluations to corroborate the results, validating that the 4-step generations from our T2V-Turbo are preferred over the 50-step DDIM samples from their teacher models, representing more than a tenfold acceleration while improving video generation quality.

PDF Details DOI

TMLR Journal 2024 Journal Article

TIGERScore: Towards Building Explainable Metric for All Text Generation Tasks

Dongfu Jiang
Yishan Li
Ge Zhang
Wenhao Huang
Bill Yuchen Lin
Wenhu Chen

We present TIGERScore, a \textbf{T}rained metric that follows \textbf{I}nstruction \textbf{G}uidance to perform \textbf{E}xplainable, and \textbf{R}eference-free evaluation over a wide spectrum of text generation tasks. Different from other automatic evaluation methods that only provide arcane scores, TIGERScore is guided by natural language instruction to provide error analysis to pinpoint the mistakes in the generated text. Our metric is based on LLaMA-2, trained on our meticulously curated instruction-tuning dataset MetricInstruct which covers 6 text generation tasks and 23 text generation datasets. The dataset consists of 42K quadruple in the form of (instruction, input, system output $\rightarrow$ error analysis). We collected the `system outputs' through from a large variety of models to cover different types of errors. To quantitatively assess our metric, we evaluate its correlation with human ratings on 5 held-in datasets, 2 held-out datasets and show that \metricname{} can achieve the open-source SoTA correlation with human ratings across these datasets and almost approaches GPT-4 evaluator. As a reference-free metric, its correlation can even surpass the best existing reference-based metrics. To further qualitatively assess the rationale generated by our metric, we conduct human evaluation on the generated explanations and found that the explanations are 70.8\% accurate. Through these experimental results, we believe \metricname{} demonstrates the possibility of building universal explainable metrics to evaluate any text generation task.

ICML Conference 2024 Conference Paper

Understanding Reasoning Ability of Language Models From the Perspective of Reasoning Paths Aggregation

Xinyi Wang 0003
Alfonso Amayuelas
Kexun Zhang
Liangming Pan
Wenhu Chen
William Yang Wang

Pre-trained language models (LMs) are able to perform complex reasoning without explicit fine-tuning. To understand how pre-training with a next-token prediction objective contributes to the emergence of such reasoning capability, we propose that we can view an LM as deriving new conclusions by aggregating indirect reasoning paths seen at pre-training time. We found this perspective effective in two important cases of reasoning: logic reasoning with knowledge graphs (KGs) and chain-of-thought (CoT) reasoning. More specifically, we formalize the reasoning paths as random walk paths on the knowledge/reasoning graphs. Analyses of learned LM distributions suggest that a weighted sum of relevant random walk path probabilities is a reasonable way to explain how LMs reason. Experiments and analysis on multiple KG and CoT datasets reveal the effect of training on random walk paths and suggest that augmenting unlabeled random walk reasoning paths can improve real-world multi-step reasoning performance.

NeurIPS Conference 2024 Conference Paper

WildVision: Evaluating Vision-Language Models in the Wild with Human Preferences

Yujie Lu
Dongfu Jiang
Wenhu Chen
William Yang Wang
Yejin Choi
Bill Yuchen Lin

Recent breakthroughs in vision-language models (VLMs) emphasize the necessity of benchmarking human preferences in real-world multimodal interactions. To address this gap, we launched WildVision-Arena (WV-Arena), an online platform that collects human preferences to evaluate VLMs. We curated WV-Bench by selecting 500 high-quality samples from 8, 000 user submissions in WV-Arena. WV-Bench uses GPT-4 as the judge to compare each VLM with Claude-3-Sonnet, achieving a Spearman correlation of 0. 94 with the WV-Arena Elo. This significantly outperforms other benchmarks like MMVet, MMMU, and MMStar. Our comprehensive analysis of 20K real-world interactions reveals important insights into the failure cases of top-performing VLMs. For example, we find that although GPT-4V surpasses many other models like Reka-Flash, Opus, and Yi-VL-Plus in simple visual recognition and reasoning tasks, it still faces challenges with subtle contextual cues, spatial reasoning, visual imagination, and expert domain knowledge. Additionally, current VLMs exhibit issues with hallucinations and safety when intentionally provoked. We are releasing our chat and feedback data to further advance research in the field of VLMs.

PDF Details DOI

TMLR Journal 2023 Journal Article

DreamEdit: Subject-driven Image Editing

Tianle Li
Max Ku
Cong Wei
Wenhu Chen

Subject-driven image generation aims at generating images containing customized subjects, which has recently drawn enormous attention from the research community. Nevertheless, the previous works cannot precisely control the background and position of the target subject. In this work, we aspire to fill the void of the existing subject-driven generation tasks. To this end, we propose two novel subject-driven editing sub-tasks, i.e., Subject Replacement and Subject Addition. The new tasks are challenging in multiple aspects: replacing a subject with a customized one can totally change its shape, texture, and color, while adding a target subject to a designated position in a provided scene necessitates a rational context-aware posture of the subject. To conquer these two novel tasks, we first manually curate a new dataset called DreamEditBench containing 22 different types of subjects, and 440 source images, which cover diverse scenarios with different difficulty levels. We plan to host DreamEditBench as a platform and hire trained evaluators for standardized human evaluation. We also devise an innovative method DreamEditor to resolve these tasks by performing iterative generation, which enables a smooth adaptation to the customized subject. In this project, we conduct automatic and human evaluations to understand the performance of our DreamEditor and baselines on DreamEditBench. We found that the new tasks are challenging for the existing models. For Subject Replacement, we found that the existing models are particularly sensitive to the shape and color of the original subject. When the original subject and the customized subject are highly different, the model failure rate will dramatically increase. For Subject Addition, we found that the existing models cannot easily blend the customized subjects into the background smoothly, which causes noticeable artifacts in the generated image. We hope that DreamEditBench can become a standardized platform to enable future investigations towards building more controllable subject-driven image editing. Our project and benchmark homepage is https://dreameditbenchteam.github.io/

NeurIPS Conference 2023 Conference Paper

MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing

Kai Zhang
Lingbo Mo
Wenhu Chen
Huan Sun
Yu Su

Text-guided image editing is widely needed in daily life, ranging from personal use to professional applications such as Photoshop. However, existing methods are either zero-shot or trained on an automatically synthesized dataset, which contains a high volume of noise. Thus, they still require lots of manual tuning to produce desirable outcomes in practice. To address this issue, we introduce MagicBrush, the first large-scale, manually annotated dataset for instruction-guided real image editing that covers diverse scenarios: single-turn, multi-turn, mask-provided, and mask-free editing. MagicBrush comprises over 10K manually annotated triplets (source image, instruction, target image), which supports trainining large-scale text-guided image editing models. We fine-tune InstructPix2Pix on MagicBrush and show that the new model can produce much better images according to human evaluation. We further conduct extensive experiments to evaluate current image editing baselines from multiple dimensions including quantitative, qualitative, and human evaluations. The results reveal the challenging nature of our dataset and the gap between current baselines and real-world editing needs.

NeurIPS Conference 2023 Conference Paper

MARBLE: Music Audio Representation Benchmark for Universal Evaluation

Ruibin Yuan
Yinghao Ma
Yizhi Li
Ge Zhang
Xingran Chen
Hanzhi Yin
zhuo le
Yiqi Liu

In the era of extensive intersection between art and Artificial Intelligence (AI), such as image generation and fiction co-creation, AI for music remains relatively nascent, particularly in music understanding. This is evident in the limited work on deep music representations, the scarcity of large-scale datasets, and the absence of a universal and community-driven benchmark. To address this issue, we introduce the Music Audio Representation Benchmark for universaL Evaluation, termed MARBLE. It aims to provide a benchmark for various Music Information Retrieval (MIR) tasks by defining a comprehensive taxonomy with four hierarchy levels, including acoustic, performance, score, and high-level description. We then establish a unified protocol based on 18 tasks on 12 public-available datasets, providing a fair and standard assessment of representations of all open-sourced pre-trained models developed on music recordings as baselines. Besides, MARBLE offers an easy-to-use, extendable, and reproducible suite for the community, with a clear statement on copyright issues on datasets. Results suggest recently proposed large-scale pre-trained musical language models perform the best in most tasks, with room for further improvement. The leaderboard and toolkit repository are published to promote future music AI research.

TMLR Journal 2023 Journal Article

Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks

Wenhu Chen
Xueguang Ma
Xinyi Wang
William W. Cohen

Recently, there has been significant progress in teaching language models to perform step-by-step reasoning to solve complex numerical reasoning tasks. Chain-of-thoughts prompting (CoT) is the state-of-art method for many of these tasks. CoT uses language models to produce text describing reasoning, and computation, and finally the answer to a question. Here we propose `Program of Thoughts' (PoT), which uses language models (mainly Codex) to generate text and programming language statements, and finally an answer. In PoT, the computation can be delegated to a program interpreter, which is used to execute the generated program, thus decoupling complex computation from reasoning and language understanding. We evaluate PoT on five math word problem datasets and three financial-QA datasets in both few-shot and zero-shot settings. We find that PoT has an average performance gain over CoT of around 12% across all datasets. By combining PoT with self-consistency decoding, we can achieve extremely strong performance on all the math datasets and financial datasets. All of our data and code will be released.

AAAI Conference 2023 Conference Paper

QA Is the New KR: Question-Answer Pairs as Knowledge Bases

William W. Cohen
Wenhu Chen
Michiel De Jong
Nitish Gupta
Alessandro Presta
Pat Verga
John Wieting

We propose a new knowledge representation (KR) based on knowledge bases (KBs) derived from text, based on question generation and entity linking. We argue that the proposed type of KB has many of the key advantages of a traditional symbolic KB: in particular, it consists of small modular components, which can be combined compositionally to answer complex queries, including relational queries and queries involving ``multi-hop'' inferences. However, unlike a traditional KB, this information store is well-aligned with common user information needs. We present one such KB, called a QEDB, and give qualitative evidence that the atomic components are high-quality and meaningful, and that atomic components can be combined in ways similar to the triples in a symbolic KB. We also show experimentally that questions reflective of typical user questions are more easily answered with a QEDB than a symbolic KB.

PDF Details DOI

ICLR Conference 2023 Conference Paper

Re-Imagen: Retrieval-Augmented Text-to-Image Generator

Wenhu Chen
Hexiang Hu
Chitwan Saharia
William W. Cohen

Research on text-to-image generation has witnessed significant progress in generating diverse and photo-realistic images, driven by diffusion and auto-regressive models trained on large-scale image-text data. Though state-of-the-art models can generate high-quality images of common entities, they often have difficulty generating images of uncommon entities, such as `Chortai (dog)' or `Picarones (food)'. To tackle this issue, we present the Retrieval-Augmented Text-to-Image Generator (Re-Imagen), a generative model that uses retrieved information to produce high-fidelity and faithful images, even for rare or unseen entities. Given a text prompt, Re-Imagen accesses an external multi-modal knowledge base to retrieve relevant (image, text) pairs, and uses them as references to generate the image. With this retrieval step, Re-Imagen is augmented with the knowledge of high-level semantics and low-level visual details of the mentioned entities, and thus improves its accuracy in generating the entities' visual appearances. We train Re-Imagen on a constructed dataset containing (image,text,retrieval) triples to teach the model to ground on both text prompt and retrieval. Furthermore, we develop a new sampling strategy to interleave the classifier-free guidance for text and retrieval condition to balance the text and retrieval alignment. Re-Imagen achieves new SoTA FID results on two image generation benchmarks, such as COCO (\ie, FID = 5.25) and WikiImage (\ie, FID = 5.82) without fine-tuning. To further evaluate the capabilities of the model, we introduce EntityDrawBench, a new benchmark that evaluates image generation for diverse entities, from frequent to rare, across multiple visual domains. Human evaluation on EntityDrawBench shows that Re-Imagen performs on par with the best prior models in photo-realism, but with significantly better real-world faithfulness, especially on less frequent entities.

NeurIPS Conference 2023 Conference Paper

Subject-driven Text-to-Image Generation via Apprenticeship Learning

Wenhu Chen
Hexiang Hu
Yandong Li
Nataniel Ruiz
Xuhui Jia
Ming-Wei Chang
William W. Cohen

Recent text-to-image generation models like DreamBooth have made remarkable progress in generating highly customized images of a target subject, by fine-tuning an ``expert model'' for a given subject from a few examples. However, this process is expensive, since a new expert model must be learned for each subject. In this paper, we present SuTI, a Subject-driven Text-to-Image generator that replaces subject-specific fine tuning with {in-context} learning. Given a few demonstrations of a new subject, SuTI can instantly generate novel renditions of the subject in different scenes, without any subject-specific optimization. SuTI is powered by {apprenticeship learning}, where a single apprentice model is learned from data generated by a massive number of subject-specific expert models. Specifically, we mine millions of image clusters from the Internet, each centered around a specific visual subject. We adopt these clusters to train a massive number of expert models, each specializing in a different subject. The apprentice model SuTI then learns to imitate the behavior of these fine-tuned experts. SuTI can generate high-quality and customized subject-specific images 20x faster than optimization-based SoTA methods. On the challenging DreamBench and DreamBench-v2, our human evaluation shows that SuTI significantly outperforms existing models like InstructPix2Pix, Textual Inversion, Imagic, Prompt2Prompt, Re-Imagen and DreamBooth.

NeurIPS Conference 2021 Conference Paper

A Dataset for Answering Time-Sensitive Questions

Wenhu Chen
Xinyi Wang
William Yang Wang

Time is an important dimension in our physical world. Lots of facts can evolve with respect to time. For example, the U. S. President might change every four years. Therefore, it is important to consider the time dimension and empower the existing QA models to reason over time. However, the existing QA datasets contain rather few time-sensitive questions, hence not suitable for diagnosing or benchmarking the model's temporal reasoning capability. In order to promote research in this direction, we propose to construct a time-sensitive QA dataset. The dataset is constructed by 1) mining time-evolving facts from WikiData and aligning them to their corresponding Wikipedia page, 2) employing crowd workers to verify and calibrate these noisy facts, 3) generating question-answer pairs based on the annotated time-sensitive facts. Our dataset poses challenges in the aspect of both temporal understanding and temporal reasoning. We evaluate different SoTA long-document QA systems like BigBird and FiD on our dataset. The best-performing model FiD can only achieve 46\% accuracy, still far behind the human performance of 87\%. We demonstrate that these models are still lacking the ability to perform consistent temporal reasoning. Therefore, we believe that our dataset could serve as a benchmark to develop NLP models more sensitive to temporal shifts.

NeurIPS Conference 2021 Conference Paper

Counterfactual Maximum Likelihood Estimation for Training Deep Networks

Xinyi Wang
Wenhu Chen
Michael Saxon
William Yang Wang

Although deep learning models have driven state-of-the-art performance on a wide array of tasks, they are prone to spurious correlations that should not be learned as predictive clues. To mitigate this problem, we propose a causality-based training framework to reduce the spurious correlations caused by observed confounders. We give theoretical analysis on the underlying general Structural Causal Model (SCM) and propose to perform Maximum Likelihood Estimation (MLE) on the interventional distribution instead of the observational distribution, namely Counterfactual Maximum Likelihood Estimation (CMLE). As the interventional distribution, in general, is hidden from the observational data, we then derive two different upper bounds of the expected negative log-likelihood and propose two general algorithms, Implicit CMLE and Explicit CMLE, for causal predictions of deep learning models using observational data. We conduct experiments on both simulated data and two real-world tasks: Natural Language Inference (NLI) and Image Captioning. The results show that CMLE methods outperform the regular MLE method in terms of out-of-domain generalization performance and reducing spurious correlations, while maintaining comparable performance on the regular evaluations.

NeurIPS Conference 2021 Conference Paper

Local Explanation of Dialogue Response Generation

Yi-Lin Tuan
Connor Pryor
Wenhu Chen
Lise Getoor
William Yang Wang

In comparison to the interpretation of classification models, the explanation of sequence generation models is also an important problem, however it has seen little attention. In this work, we study model-agnostic explanations of a representative text generation task -- dialogue response generation. Dialog response generation is challenging with its open-ended sentences and multiple acceptable responses. To gain insights into the reasoning process of a generation model, we propose a new method, local explanation of response generation (LERG) that regards the explanations as the mutual interaction of segments in input and output sentences. LERG views the sequence prediction as uncertainty estimation of a human response and then creates explanations by perturbing the input and calculating the certainty change over the human response. We show that LERG adheres to desired properties of explanations for text generation including unbiased approximation, consistency and cause identification. Empirically, our results show that our method consistently improves other widely used methods on proposed automatic- and human- evaluation metrics for this new task by $4. 4$-$12. 8$\%. Our analysis demonstrates that LERG can extract both explicit and implicit relations between input and output segments.

ICLR Conference 2021 Conference Paper

Open Question Answering over Tables and Text

Wenhu Chen
Ming-Wei Chang
Eva Schlinger
William Yang Wang
William W. Cohen

In open question answering (QA), the answer to a question is produced by retrieving and then analyzing documents that might contain answers to the question. Most open QA systems have considered only retrieving information from unstructured text. Here we consider for the first time open QA over {\em both} tabular and textual data and present a new large-scale dataset \emph{Open Table-and-Text Question Answering} (OTT-QA) to evaluate performance on this task. Most questions in OTT-QA require multi-hop inference across tabular data and unstructured text, and the evidence required to answer a question can be distributed in different ways over these two types of input, making evidence retrieval challenging---our baseline model using an iterative retriever and BERT-based reader achieves an exact match score less than 10\%. We then propose two novel techniques to address the challenge of retrieving and aggregating evidence for OTT-QA. The first technique is to use ``early fusion'' to group multiple highly relevant tabular and textual units into a fused block, which provides more context for the retriever to search for. The second technique is to use a cross-block reader to model the cross-dependency between multiple retrieved evidence with global-local sparse attention. Combining these two techniques improves the score significantly, to above 27\%.

AAAI Conference 2020 Conference Paper

Generative Adversarial Zero-Shot Relational Learning for Knowledge Graphs

Pengda Qin
Xin Wang
Wenhu Chen
Chunyun Zhang
Weiran Xu
William Yang Wang

Large-scale knowledge graphs (KGs) are shown to become more important in current information systems. To expand the coverage of KGs, previous studies on knowledge graph completion need to collect adequate training instances for newlyadded relations. In this paper, we consider a novel formulation, zero-shot learning, to free this cumbersome curation. For newly-added relations, we attempt to learn their semantic features from their text descriptions and hence recognize the facts of unseen relations with no examples being seen. For this purpose, we leverage Generative Adversarial Networks (GANs) to establish the connection between text and knowledge graph domain: The generator learns to generate the reasonable relation embeddings merely with noisy text descriptions. Under this setting, zero-shot learning is naturally converted to a traditional supervised classiﬁcation task. Empirically, our method is model-agnostic that could be potentially applied to any version of KG embeddings, and consistently yields performance improvements on NELL and Wiki dataset.

ICLR Conference 2020 Conference Paper

TabFact: A Large-scale Dataset for Table-based Fact Verification

Wenhu Chen
Hongmin Wang
Jianshu Chen
Yunkai Zhang 0002
Hong Wang 0023
Shiyang Li
Xiyou Zhou
William Yang Wang

The problem of verifying whether a textual hypothesis holds based on the given evidence, also known as fact verification, plays an important role in the study of natural language understanding and semantic representation. However, existing studies are mainly restricted to dealing with unstructured evidence (e.g., natural language sentences and documents, news, etc), while verification under structured evidence, such as tables, graphs, and databases, remains unexplored. This paper specifically aims to study the fact verification given semi-structured data as evidence. To this end, we construct a large-scale dataset called TabFact with 16k Wikipedia tables as the evidence for 118k human-annotated natural language statements, which are labeled as either ENTAILED or REFUTED. TabFact is challenging since it involves both soft linguistic reasoning and hard symbolic reasoning. To address these reasoning challenges, we design two different models: Table-BERT and Latent Program Algorithm (LPA). Table-BERT leverages the state-of-the-art pre-trained language model to encode the linearized tables and statements into continuous vectors for verification. LPA parses statements into LISP-like programs and executes them against the tables to obtain the returned binary value for verification. Both methods achieve similar accuracy but still lag far behind human performance. We also perform a comprehensive analysis to demonstrate great future opportunities.

NeurIPS Conference 2019 Conference Paper

Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting

Shiyang Li
Xiaoyong Jin
Yao Xuan
Xiyou Zhou
Wenhu Chen
Yu-Xiang Wang
Xifeng Yan

Time series forecasting is an important problem across many domains, including predictions of solar plant energy output, electricity consumption, and traffic jam situation. In this paper, we propose to tackle such forecasting problem with Transformer. Although impressed by its performance in our preliminary study, we found its two major weaknesses: (1) locality-agnostics: the point-wise dot- product self-attention in canonical Transformer architecture is insensitive to local context, which can make the model prone to anomalies in time series; (2) memory bottleneck: space complexity of canonical Transformer grows quadratically with sequence length L, making directly modeling long time series infeasible. In order to solve these two issues, we first propose convolutional self-attention by producing queries and keys with causal convolution so that local context can be better incorporated into attention mechanism. Then, we propose LogSparse Transformer with only O(L(log L)^2) memory cost, improving forecasting accuracy for time series with fine granularity and strong long-term dependencies under constrained memory budget. Our experiments on both synthetic data and real- world datasets show that it compares favorably to the state-of-the-art.