Arrow Research search

Author name cluster

Dahua Lin

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.

74 papers
2 author rows

Possible papers

74

AAAI Conference 2026 Conference Paper

MathSmith: Towards Extremely Hard Mathematical Reasoning by Forging Synthetic Problems with a Reinforced Policy

  • Shaoxiong Zhan
  • Yanlin Lai
  • Ziyu Lu
  • Dahua Lin
  • Ziqing Yang
  • Fei Tan

Large language models have achieved substantial progress in mathematical reasoning, yet their advancement is limited by the scarcity of high-quality, high-difficulty training data. Existing synthesis methods largely rely on transforming human-written templates, limiting both diversity and scalability. We propose MathSmith, a novel framework for synthesizing challenging mathematical problems to enhance LLM reasoning. Rather than modifying existing problems, MathSmith constructs new ones from scratch by randomly sampling concept–explanation pairs from PlanetMath, ensuring data independence and avoiding contamination. To increase difficulty, we design nine predefined strategies as soft constraints during rationales. We further adopts reinforcement learning to jointly optimize structural validity, reasoning complexity, and answer consistency. The length of the reasoning trace generated under autoregressive prompting is used to reflect cognitive complexity, encouraging the creation of more demanding problems aligned with long-chain-of-thought reasoning. Experiments across five benchmarks, categorized as easy & medium (GSM8K, MATH-500) and hard (AIME2024, AIME2025, OlympiadBench), show that MathSmith consistently outperforms existing baselines under both short and long CoT settings. Additionally, a weakness-focused variant generation module enables targeted improvement on specific concepts. Overall, MathSmith exhibits strong scalability, generalization, and transferability, highlighting the promise of high-difficulty synthetic data in advancing LLM reasoning capabilities.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling

  • Hao Li
  • Shuai Yang
  • Yilun Chen
  • Xinyi Chen
  • Xiaoda Yang
  • Yang Tian
  • Hanqing Wang
  • Tai WANG

Recent vision-language-action (VLA) models built on pretrained vision-language models (VLMs) have demonstrated strong performance in robotic manipulation. However, these models remain constrained by the single-frame image paradigm and fail to fully leverage the temporal information offered by multi-frame histories, as directly feeding multiple frames into VLM backbones incurs substantial computational overhead and inference latency. We propose CronusVLA, a unified framework that extends single-frame VLA models to the multi-frame paradigm. CronusVLA follows a two-stage process: (1) Single-frame pretraining on large-scale embodied datasets with autoregressive prediction of action tokens, establishing an effective embodied vision-language foundation; (2) Multi-frame post-training, which adapts the prediction of the vision-language backbone from discrete tokens to learnable features, and aggregates historical information via feature chunking. CronusVLA effectively addresses the existing challenges of multi-frame modeling while enhancing performance. To evaluate the robustness under temporal and spatial disturbances, we introduce SimplerEnv-OR, a novel benchmark featuring 24 types of observational disturbances and 120 severity levels. Experiments across three embodiments in simulated and real-world environments demonstrate that CronusVLA achieves leading performance and superior robustness, with a 70.9% success rate on SimplerEnv, a 26.8% improvement over OpenVLA on LIBERO, and the highest robustness score on SimplerEnv-OR, showing the promise of efficient multi-frame adaptation for real-world VLA deployment.

PDF Details DOI

ICLR Conference 2025 Conference Paper

3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation

  • Xiao Fu
  • Xian Liu
  • Xintao Wang 0002
  • Sida Peng
  • Menghan Xia
  • Xiaoyu Shi 0002
  • Ziyang Yuan
  • Pengfei Wan 0001

This paper aims to manipulate multi-entity 3D motions in video generation. Previous methods on controllable video generation primarily leverage 2D control signals to manipulate object motions and have achieved remarkable synthesis results. However, 2D control signals are inherently limited in expressing the 3D nature of object motions. To overcome this problem, we introduce 3DTrajMaster, a robust controller that regulates multi-entity dynamics in 3D space, given user-desired 6DoF pose (location and rotation) sequences of entities. At the core of our approach is a plug-and-play 3D-motion grounded object injector that fuses multiple input entities with their respective 3D trajectories through a gated self-attention mechanism. In addition, we exploit an injector architecture to preserve the video diffusion prior, which is crucial for generalization ability. To mitigate video quality degradation, we introduce a domain adaptor during training and employ an annealed sampling strategy during inference. To address the lack of suitable training data, we construct a 360-Motion Dataset, which first correlates collected 3D human and animal assets with GPT-generated trajectory and then captures their motion with 12 evenly-surround cameras on diverse 3D UE platforms. Extensive experiments show that 3DTrajMaster sets a new state-of-the-art in both accuracy and generalization for controlling multi-entity 3D motions. Project page: http://fuxiao0719.github.io/projects/3dtrajmaster

Details

NeurIPS Conference 2025 Conference Paper

Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity

  • Yuhan Zhang
  • Long Zhuo
  • Ziyang Chu
  • Tong Wu
  • Zhibing Li
  • Liang Pan
  • Dahua Lin
  • Ziwei Liu

Despite rapid advances in 3D content generation, quality assessment for the generated 3D assets remains challenging. Existing methods mainly rely on image-based metrics and operate solely at the object level, limiting their ability to capture spatial Despite rapid advances in 3D content generation, quality assessment for the generated 3D assets remains challenging. Existing methods mainly rely on image-based metrics and operate solely at the object level, limiting their ability to capture spatial coherence, material authenticity, and high-fidelity local details. 1) To address these challenges, we introduce Hi3DEval, a hierarchical evaluation framework tailored for 3D generative content. It combines both object-level and part-level evaluation, enabling holistic assessments across multiple dimensions as well as fine-grained quality analysis. Additionally, we extend texture evaluation beyond aesthetic appearance by explicitly assessing material realism, focusing on attributes such as albedo, saturation, and metallicness. 2) To support this framework, we construct Hi3DBench, a large-scale dataset comprising diverse 3D assets and high-quality annotations, accompanied by a reliable multi-agent annotation pipeline. We further propose a 3D-aware automated scoring system based on hybrid 3D representations. Specifically, we leverage video-based representations for object-level and material-subject evaluations to enhance modeling of spatio-temporal consistency and employ pretrained 3D features for part-level perception. Extensive experiments demonstrate that our approach outperforms existing image-based metrics in modeling 3D characteristics and achieves superior alignment with human preference, providing a scalable alternative to manual evaluations.

PDF Details

NeurIPS Conference 2025 Conference Paper

Hierachical Balance Packing: Towards Efficient Supervised Fine-tuning for Long-Context LLM

  • Yongqiang Yao
  • Jingru Tan
  • Kaihuan Liang
  • Feizhao Zhang
  • Jiahao Hu
  • Shuo Wu
  • Yazhe Niu
  • Ruihao Gong

Training Long-Context Large Language Models (LLMs) is challenging, as hybrid training with long-context and short-context data often leads to workload imbalances. Existing works mainly use data packing to alleviate this issue, but fail to consider imbalanced attention computation and wasted communication overhead. This paper proposes Hierarchical Balance Packing (HBP), which designs a novel batch-construction method and training recipe to address those inefficiencies. In particular, the HBP constructs multi-level data packing groups, each optimized with a distinct packing length. It assigns training samples to their optimal groups and configures each group with the most effective settings, including sequential parallelism degree and gradient checkpointing configuration. To effectively utilize multi-level groups of data, we design a dynamic training pipeline specifically tailored to HBP, including curriculum learning, adaptive sequential parallelism, and stable loss. Our extensive experiments demonstrate that our method significantly reduces training time over multiple datasets and open-source models while maintaining strong performance. For the largest DeepSeek-V2 (236B) MoE model, our method speeds up the training by 2. 4$\times$ with competitive performance. Codes will be released at https: //github. com/ModelTC/HBP.

PDF Details

NeurIPS Conference 2025 Conference Paper

HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance

  • Jiazi Bu
  • Pengyang Ling
  • Yujie Zhou
  • Pan Zhang
  • Tong Wu
  • Xiaoyi Dong
  • Yuhang Zang
  • Yuhang Cao

Text-to-image (T2I) diffusion/flow models have drawn considerable attention recently due to their remarkable ability to deliver flexible visual creations. Still, high-resolution image synthesis presents formidable challenges due to the scarcity and complexity of high-resolution content. Recent approaches have investigated training-free strategies to enable high-resolution image synthesis with pre-trained models. However, these techniques often struggle with generating high-quality visuals and tend to exhibit artifacts or low-fidelity details, as they typically rely solely on the endpoint of the low-resolution sampling trajectory while neglecting intermediate states that are critical for preserving structure and synthesizing finer detail. To this end, we present HiFlow, a training-free and model-agnostic framework to unlock the resolution potential of pre-trained flow models. Specifically, HiFlow establishes a virtual reference flow within the high-resolution space that effectively captures the characteristics of low-resolution flow information, offering guidance for high-resolution generation through three key aspects: initialization alignment for low-frequency consistency, direction alignment for structure preservation, and acceleration alignment for detail fidelity. By leveraging such flow-aligned guidance, HiFlow substantially elevates the quality of high-resolution image synthesis of T2I models and demonstrates versatility across their personalized variants. Extensive experiments validate HiFlow's capability in achieving superior high-resolution image quality over state-of-the-art methods.

PDF Details

ICLR Conference 2025 Conference Paper

IDArb: Intrinsic Decomposition for Arbitrary Number of Input Views and Illuminations

  • Zhibing Li
  • Tong Wu
  • Jing Tan 0002
  • Mengchen Zhang 0001
  • Jiaqi Wang 0003
  • Dahua Lin

Capturing geometric and material information from images remains a fundamental challenge in computer vision and graphics. Traditional optimization-based methods often require hours of computational time to reconstruct geometry, material properties, and environmental lighting from dense multi-view inputs, while still struggling with inherent ambiguities between lighting and material. On the other hand, learning-based approaches leverage rich material priors from existing 3D object datasets but face challenges with maintaining multi-view consistency. In this paper, we introduce IDArb, a diffusion-based model designed to perform intrinsic decomposition on an arbitrary number of images under varying illuminations. Our method achieves highly accurate and multi-view consistent estimation on surface normals and material properties. This is made possible through a novel cross-view, cross-domain attention module and an illumination-augmented, view-adaptive training strategy. Additionally, we introduce ARB-Objaverse, a new dataset that provides large-scale multi-view intrinsic data and renderings under diverse lighting conditions, supporting robust training. Extensive experiments demonstrate that IDArb outperforms state-of-the-art methods both qualitatively and quantitatively. Moreover, our approach facilitates a range of downstream tasks, including single-image relighting, photometric stereo, and 3D reconstruction, highlighting its broad applicability in realistic 3D content creation. Project website: https://lizb6626.github.io/IDArb/.

Details

NeurIPS Conference 2025 Conference Paper

Imagine360: Immersive 360 Video Generation from Perspective Anchor

  • Jing Tan
  • Shuai Yang
  • Tong Wu
  • Jingwen He
  • Yuwei Guo
  • Ziwei Liu
  • Dahua Lin

$360^\circ$ videos offer a hyper-immersive experience that allows the viewers to explore a dynamic scene from full 360 degrees. To achieve more accessible and personalized content creation in $360^\circ$ video format, we seek to lift standard perspective videos into $360^\circ$ equirectangular videos. To this end, we introduce **Imagine360**, the first perspective-to-$360^\circ$ video generation framework that creates high-quality $360^\circ$ videos with rich and diverse motion patterns from video anchors. Imagine360 learns fine-grained spherical visual and motion patterns from limited $360^\circ$ video data with several key designs. **1)** Firstly we adopt the dual-branch design, including a perspective and a panorama video denoising branch to provide local and global constraints for $360^\circ$ video generation, with motion module and spatial LoRA layers fine-tuned on $360^\circ$ videos. **2)** Additionally, an antipodal mask is devised to capture long-range motion dependencies, enhancing the reversed camera motion between antipodal pixels across hemispheres. **3)** To handle diverse perspective video inputs, we propose rotation-aware designs that adapt to varying video masking due to changing camera poses across frames. **4)** Lastly, we introduce a new 360 video dataset featuring 10K high-quality, trimmed 360 video clips with structured motion to facilitate training. Extensive experiments show Imagine360 achieves superior graphics quality and motion coherence with our curated dataset among state-of-the-art $360^\circ$ video generation methods. We believe Imagine360 holds promise for advancing personalized, immersive $360^\circ$ video creation.

PDF Details

ICLR Conference 2025 Conference Paper

LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models

  • Junyan Ye
  • Baichuan Zhou
  • Zilong Huang
  • Junan Zhang
  • Tianyi Bai
  • Hengrui Kang
  • Jun He
  • Honglin Lin

With the rapid development of AI-generated content, the future internet may be inundated with synthetic data, making the discrimination of authentic and credible multimodal data increasingly challenging. Synthetic data detection has thus garnered widespread attention, and the performance of large multimodal models (LMMs) in this task has attracted significant interest. LMMs can provide natural language explanations for their authenticity judgments, enhancing the explainability of synthetic content detection. Simultaneously, the task of distinguishing between real and synthetic data effectively tests the perception, knowledge, and reasoning capabilities of LMMs. In response, we introduce LOKI, a novel benchmark designed to evaluate the ability of LMMs to detect synthetic data across multiple modalities. LOKI encompasses video, image, 3D, text, and audio modalities, comprising 18K carefully curated questions across 26 subcategories with clear difficulty levels. The benchmark includes coarse-grained judgment and multiple-choice questions, as well as fine-grained anomaly selection and explanation tasks, allowing for a comprehensive analysis of LMMs. We evaluated 22 open-source LMMs and 6 closed-source models on LOKI, highlighting their potential as synthetic data detectors and also revealing some limitations in the development of LMM capabilities. More information about LOKI can be found at https://opendatalab.github.io/LOKI/.

Details

ICLR Conference 2025 Conference Paper

Mask-DPO: Generalizable Fine-grained Factuality Alignment of LLMs

  • Yuzhe Gu
  • Wenwei Zhang
  • Chengqi Lyu
  • Dahua Lin
  • Kai Chen 0026

Large language models (LLMs) exhibit hallucinations (i.e., unfaithful or nonsensical information) when serving as AI assistants in various domains. Since hallucinations always come with truthful content in the LLM responses, previous factuality alignment methods that conduct response-level preference learning inevitably introduced noises during training. Therefore, this paper proposes a fine-grained factuality alignment method based on Direct Preference Optimization (DPO), called Mask-DPO. Incorporating sentence-level factuality as mask signals, Mask-DPO only learns from factually correct sentences in the preferred samples and prevents the penalty on factual contents in the not preferred samples, which resolves the ambiguity in the preference learning. Extensive experimental results demonstrate that Mask-DPO can significantly improve the factuality of LLMs responses to questions from both in-domain and out-of-domain datasets, although these questions and their corresponding topics are unseen during training. Only trained on the ANAH train set, the score of Llama3.1-8B-Instruct on the ANAH test set is improved from 49.19% to 77.53%, even surpassing the score of Llama3.1-70B-Instruct (53.44%), while its FactScore on the out-of-domain Biography dataset is also improved from 30.29% to 39.39%. We further study the generalization property of Mask-DPO using different training sample scaling strategies and find that scaling the number of topics in the dataset is more effective than the number of questions. We provide a hypothesis of what factual alignment is doing with LLMs, on the implication of this phenomenon, and conduct proof-of-concept experiments to verify it. We hope the method and the findings pave the way for future research on scaling factuality alignment.

Details

ICLR Conference 2025 Conference Paper

MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models

  • Ziyu Liu
  • Yuhang Zang
  • Xiaoyi Dong
  • Pan Zhang 0001
  • Yuhang Cao
  • Haodong Duan
  • Conghui He
  • Yuanjun Xiong

Visual preference alignment involves training Large Vision-Language Models (LVLMs) to predict human preferences between visual inputs. This is typically achieved by using labeled datasets of chosen/rejected pairs and employing optimization algorithms like direct preference optimization (DPO). Existing visual alignment methods, primarily designed for single-image scenarios, struggle to effectively handle the complexity of multi-image tasks due to the scarcity of diverse training data and the high cost of annotating chosen/rejected pairs. We present Multi-Image Augmented Direct Preference Optimization (MIA-DPO), a visual preference alignment approach that effectively handles multi-image inputs. MIA-DPO mitigates the scarcity of diverse multi-image training data by extending single-image data with unrelated images arranged in grid collages or pic-in-pic formats, significantly reducing the costs associated with multi-image data annotations. Our observation reveals that attention values of LVLMs vary considerably across different images. We use attention values to identify and filter out rejected responses the model may have mistakenly focused on. Our attention-aware selection for constructing the chosen/rejected pairs without relying on (i) human annotation, (ii) extra data, and (iii) external models or APIs. MIA-DPO is compatible with various architectures and outperforms existing methods on five multi-image benchmarks, achieving an average performance boost of 3.0% on LLaVA-v1.5 and 4.3% on the recent InternLM-XC2.5. Moreover, MIA-DPO has a minimal effect on the model's ability to understand single images.

Details

NeurIPS Conference 2025 Conference Paper

Mixing Expert Knowledge: Bring Human Thoughts Back To the Game of Go

  • Yichuan Ma
  • Linyang Li
  • Yongkang Chen
  • Peiji Li
  • Jiasheng Ye
  • Qipeng Guo
  • Dahua Lin
  • Kai Chen

Large language models (LLMs) have demonstrated exceptional performance in reasoning tasks such as mathematics and coding, matching or surpassing human capabilities. However, these impressive reasoning abilities face significant challenges in specialized domains. Taking Go as an example, although AlphaGo has established the high performance ceiling of AI systems in Go, mainstream LLMs still struggle to reach even beginner-level proficiency, let alone perform natural language reasoning. This performance gap between general-purpose LLMs and domain experts is significantly limiting the application of LLMs on a wider range of domain-specific tasks. In this work, we aim to bridge the divide between LLMs' general reasoning capabilities and expert knowledge in domain-specific tasks. We perform mixed fine-tuning with structured Go expertise and general long Chain-of-Thought (CoT) reasoning data as a cold start, followed by reinforcement learning to integrate expert knowledge in Go with general reasoning capabilities. Through this methodology, we present LoGos, a powerful LLM that not only maintains outstanding general reasoning abilities, but also conducts Go gameplay in natural language, demonstrating effective strategic reasoning and accurate next-move prediction. LoGos achieves performance comparable to human professional players, substantially surpassing all existing LLMs. Through this work, we aim to contribute insights on applying general LLM reasoning capabilities to specialized domains. We will release the first large-scale Go dataset for LLM training, the first LLM Go evaluation benchmark, and the first general LLM that reaches human expert-level performance in Go.

PDF Details

ICML Conference 2025 Conference Paper

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design

  • Haojie Duanmu
  • Xiuhong Li
  • Zhihang Yuan
  • Size Zheng 0001
  • Jiangfei Duan
  • Xingcheng Zhang
  • Dahua Lin

Mixture-of-Experts (MoE) models face deployment challenges due to their large parameter counts and computational demands. We explore quantization for MoE models and highlight two key insights: 1) linear blocks exhibit varying quantization sensitivity, and 2) divergent expert activation frequencies create heterogeneous computational characteristics. Based on these observations, we introduce MxMoE, a mixed-precision optimization framework for MoE models that considers both algorithmic and system perspectives. MxMoE navigates the design space defined by parameter sensitivity, expert activation dynamics, and hardware resources to derive efficient mixed-precision configurations. Additionally, MxMoE automatically generates optimized mixed-precision GroupGEMM kernels, enabling parallel execution of GEMMs with different precisions. Evaluations show that MxMoE outperforms existing methods, achieving 2. 4 lower Wikitext-2 perplexity than GPTQ at 2. 25-bit and delivering up to 3. 4x speedup over full precision, as well as up to 29. 4% speedup over uniform quantization at equivalent accuracy with 5-bit weight-activation quantization. Our code is available at https: //github. com/cat538/MxMoE.

Details

ICML Conference 2025 Conference Paper

OmniBal: Towards Fast Instruction-Tuning for Vision-Language Models via Omniverse Computation Balance

  • Yongqiang Yao
  • Jingru Tan
  • Feizhao Zhang
  • Jiahao Hu
  • Yazhe Niu
  • Xin Jin 0008
  • Bo Li 0126
  • Pengfei Liu 0003

Vision-language instruction-tuning models have recently achieved significant performance improvements. In this work, we discover that large-scale 3D parallel training on those models leads to an imbalanced computation load across different devices. The vision and language parts are inherently heterogeneous: their data distribution and model architecture differ significantly, which affects distributed training efficiency. To address this issue, we rebalance the computational load from data, model, and memory perspectives, achieving more balanced computation across devices. Specifically, for the data, instances are grouped into new balanced mini-batches within and across devices. A search-based method is employed for the model to achieve a more balanced partitioning. For memory optimization, we adaptively adjust the re-computation strategy for each partition to utilize the available memory fully. These three perspectives are not independent but are closely connected, forming an omniverse balanced training framework. Extensive experiments are conducted to validate the effectiveness of our method. Compared with the open-source training code of InternVL-Chat, training time is reduced greatly, achieving about 1. 8$\times$ speed-up. Our method’s efficacy and generalizability are further validated across various models and datasets. Codes will be released at https: //github. com/ModelTC/OmniBal.

Details

ICLR Conference 2025 Conference Paper

Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulation

  • Yang Tian
  • Sizhe Yang
  • Jia Zeng
  • Ping Wang
  • Dahua Lin
  • Hao Dong 0003
  • Jiangmiao Pang

Current efforts to learn scalable policies in robotic manipulation primarily fall into two categories: one focuses on "action," which involves behavior cloning from extensive collections of robotic data, while the other emphasizes "vision," enhancing model generalization by pre-training representations or generative models, also referred to as world models, using large-scale visual datasets. This paper presents an end-to-end paradigm that predicts actions using inverse dynamics models conditioned on the robot's forecasted visual states, named Predictive Inverse Dynamics Models (PIDM). By closing the loop between vision and action, the end-to-end PIDM can be a better scalable action learner. In practice, we use Transformers to process both visual states and actions, naming the model Seer. It is initially pre-trained on large-scale robotic datasets, such as DROID, and can be adapted to real-world scenarios with a little fine-tuning data. Thanks to large-scale, end-to-end training and the continuous synergy between vision and action at each execution step, Seer significantly outperforms state-of-the-art methods across both simulation and real-world experiments. It achieves improvements of 13% on the LIBERO-LONG benchmark, 22% on CALVIN ABC-D, and 43% in real-world tasks. Notably, it demonstrates superior generalization for novel objects, lighting conditions, and environments under high-intensity disturbances. Code and models will be publicly available.

Details

NeurIPS Conference 2025 Conference Paper

Semi-off-Policy Reinforcement Learning for Vision-Language Slow-Thinking Reasoning

  • Junhao Shen
  • Haiteng Zhao
  • Yuzhe Gu
  • Songyang Gao
  • Kuikun Liu
  • Haian Huang
  • Jianfei Gao
  • Dahua Lin

Enhancing large vision-language models (LVLMs) with visual slow-thinking reasoning is crucial for solving complex multimodal tasks. However, since LVLMs are mainly trained with vision-language alignment, it is difficult to adopt on-policy reinforcement learning (RL) to develop the slow thinking ability because the rollout space is restricted by its initial abilities. Off-policy RL offers a way to go beyond the current policy, but directly distilling trajectories from external models may cause visual hallucinations due to mismatched visual perception abilities across models. To address these issues, this paper proposes SOPHIA, a simple and scalable S emi- O ff- P olicy RL for vision-language slow-t HI nking re A soning. SOPHIA builds a semi-off-policy behavior model by combining on-policy visual understanding from a trainable LVLM with off-policy slow-thinking reasoning from a language model, assigns outcome-based rewards to reasoning, and propagates visual rewards backward. Then LVLM learns slow-thinking reasoning ability from the obtained reasoning trajectories using propagated rewards via off-policy RL algorithms. Extensive experiments with InternVL2. 5 and InternVL3. 0 with 8B and 38B sizes show the effectiveness of SOPHIA. Notably, SOPHIA improves InternVL3. 0-38B by 8. 50\% in average, reaching state-of-the-art performance among open-source LVLMs on multiple multimodal reasoning benchmarks, and even outperforms some closed-source models (e. g. , GPT-4. 1) on the challenging MathVision and OlympiadBench, achieving 49. 08\% and 49. 95\% pass@1 accuracy, respectively. Analysis shows SOPHIA outperforms supervised fine-tuning and direct on-policy RL methods, offering a better policy initialization for further on-policy training.

PDF Details

ICML Conference 2025 Conference Paper

SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation

  • Zihan Liu
  • Shuangrui Ding
  • Zhixiong Zhang
  • Xiaoyi Dong
  • Pan Zhang 0001
  • Yuhang Zang
  • Yuhang Cao
  • Dahua Lin

Text-to-song generation, the task of creating vocals and accompaniment from textual inputs, poses significant challenges due to domain complexity and data scarcity. Existing approaches often employ multi-stage generation procedures, leading to cumbersome training and inference pipelines, as well as suboptimal overall generation quality due to error accumulation across stages. In this paper, we propose SongGen, a fully open-source, single-stage auto-regressive transformer designed for controllable song generation. The proposed model facilitates fine-grained control over diverse musical attributes, including lyrics and textual descriptions of instrumentation, genre, mood, and timbre, while also offering an optional three-second reference clip for voice cloning. Within a unified auto-regressive framework, SongGen supports two output modes: mixed mode, which generates a mixture of vocals and accompaniment directly, and dual-track mode, which synthesizes them separately for greater flexibility in downstream applications. We explore diverse token pattern strategies for each mode, leading to notable improvements and valuable insights. Furthermore, we design an automated data preprocessing pipeline with effective quality control. To foster community engagement and future research, we will release our model weights, training code, annotated data, and preprocessing pipeline. The code is available at https: //github. com/LiuZH-19/SongGen.

Details

AAAI Conference 2025 Conference Paper

UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban Scenarios

  • Baichuan Zhou
  • Haote Yang
  • Dairong Chen
  • Junyan Ye
  • Tianyi Bai
  • Jinhua Yu
  • Songyang Zhang
  • Dahua Lin

Recent evaluations of Large Multimodal Models (LMMs) have explored their capabilities in various domains, with only few benchmarks specifically focusing on urban environments. Moreover, existing urban benchmarks have been limited to evaluating LMMs with basic region-level urban tasks under singular views, leading to incomplete evaluations of LMMs' abilities in urban environments. To address these issues, we present UrBench, a comprehensive benchmark designed for evaluating LMMs in complex multi-view urban scenarios. UrBench contains 11.6K meticulously curated questions at both region-level and role-level that cover 4 task dimensions: Geo-Localization, Scene Reasoning, Scene Understanding, and Object Understanding, totaling 14 task types. In constructing UrBench, we utilize data from existing datasets and additionally collect data from 11 cities, creating new annotations using a cross-view detection-matching method. With these images and annotations, we then integrate LMM-based, rule-based, and human-based methods to construct large-scale high-quality questions. Our evaluations on 21 LMMs show that current LMMs struggle in the urban environments in several aspects. Even the best performing GPT-4o lags behind humans in most tasks, ranging from simple tasks such as counting to complex tasks such as orientation, localization and object attribute recognition, with an average performance gap of 17.4%. Our benchmark also reveals that LMMs exhibit inconsistent behaviors with different urban views, especially with respect to understanding cross-view relations.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Utilize the Flow Before Stepping into the Same River Twice: Certainty Represented Knowledge Flow for Refusal-Aware Instruction Tuning

  • Runchuan Zhu
  • Zhipeng Ma
  • Jiang Wu
  • Junyuan Gao
  • Jiaqi Wang
  • Dahua Lin
  • Conghui He

Refusal-Aware Instruction Tuning (RAIT) enables Large Language Models (LLMs) to refuse to answer unknown questions. By modifying responses of unknown questions in the training data to refusal responses such as ''I don't know", RAIT enhances the reliability of LLMs and reduces their hallucination. Generally, RAIT modifies training samples based on the correctness of the initial LLM's response. However, this crude approach can cause LLMs to excessively refuse answering questions they could have correctly answered, the problem we call over-refusal. In this paper, we explore two primary causes of over-refusal: Static conflict occurs when similar samples within the LLM’s feature space receive differing supervision signals (original vs. modified ''I don't know"). Dynamic conflict arises as the LLM's evolving knowledge during SFT enables it to answer previously unanswerable questions, but the now-answerable training samples still retain the original ''I don't know" supervision signals from the initial LLM state, leading to inconsistencies. These conflicts cause the trained LLM to misclassify known questions as unknown, resulting in over-refusal. To address this issue, we introduce Certainty Represented Knowledge Flow for Refusal-Aware Instructions Tuning (CRaFT). CRaFT centers on two main contributions: First, we additionally incorporate response certainty to selectively filter and modify data, reducing static conflicts. Second, we implement preliminary rehearsal training to characterize changes in the LLM's knowledge state, which helps mitigate dynamic conflicts during the fine-tuning process. We conducted extensive experiments on open-ended question answering and multiple-choice question task. Experiment results show that CRaFT can improve LLM's overall performance during the RAIT process.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Video World Models with Long-term Spatial Memory

  • Tong Wu
  • Shuai Yang
  • Ryan Po
  • Yinghao Xu
  • Ziwei Liu
  • Dahua Lin
  • Gordon Wetzstein

Emerging world models autoregressively generate video frames in response to actions, such as camera movements and text prompts, among other control signals. Due to limited temporal context window sizes, these models often struggle to maintain scene consistency during revisits, leading to severe forgetting of previously generated environments. Inspired by the mechanisms of human memory, we introduce a novel framework to enhancing long-term consistency of video world models through a geometry-grounded long-term spatial memory. Our framework includes mechanisms to store and retrieve information from the long-term spatial memory and we curate custom datasets to train and evaluate world models with explicitly stored 3D memory mechanisms. Our evaluations show improved quality, consistency, and context length compared to relevant baselines, paving the way towards long-term consistent world generation.

PDF Details

ICML Conference 2025 Conference Paper

VideoRoPE: What Makes for Good Video Rotary Position Embedding?

  • Xilin Wei
  • Xiaoran Liu
  • Yuhang Zang
  • Xiaoyi Dong
  • Pan Zhang 0001
  • Yuhang Cao
  • Jian Tong
  • Haodong Duan

While Rotary Position Embedding (RoPE) and its variants are widely adopted for their long-context capabilities, the extension of the 1D RoPE to video, with its complex spatio-temporal structure, remains an open challenge. This work first introduces a comprehensive analysis that identifies four key characteristics essential for the effective adaptation of RoPE to video, which have not been fully considered in prior work. As part of our analysis, we introduce a challenging V-NIAH-D (Visual Needle-In-A-Haystack with Distractors) task, which adds periodic distractors into V-NIAH. The V-NIAH-D task demonstrates that previous RoPE variants, lacking appropriate temporal dimension allocation, are easily misled by distractors. Based on our analysis, we introduce VideoRoPE, with a 3D structure designed to preserve spatio-temporal relationships. VideoRoPE features low-frequency temporal allocation to mitigate periodic oscillations, a diagonal layout to maintain spatial symmetry, and adjustable temporal spacing to decouple temporal and spatial indexing. VideoRoPE consistently surpasses previous RoPE variants, across diverse downstream tasks such as long video retrieval, video understanding, and video hallucination. Our code and model weights will be publicly released.

Details

NeurIPS Conference 2024 Conference Paper

AlchemistCoder: Harmonizing and Eliciting Code Capability by Hindsight Tuning on Multi-source Data

  • Zifan Song
  • Yudong Wang
  • Wenwei Zhang
  • Kuikun Liu
  • Chengqi Lyu
  • Demin Song
  • Qipeng Guo
  • Hang Yan

Open-source Large Language Models (LLMs) and their specialized variants, particularly Code LLMs, have recently delivered impressive performance. However, previous Code LLMs are typically fine-tuned on single-source data with limited quality and diversity, which may insufficiently elicit the potential of pre-trained Code LLMs. In this paper, we present AlchemistCoder, a series of Code LLMs with enhanced code generation and generalization capabilities fine-tuned on multi-source data. To achieve this, we pioneer to unveil inherent conflicts among the various styles and qualities in multi-source code corpora and introduce data-specific prompts with hindsight relabeling, termed AlchemistPrompts, to harmonize different data sources and instruction-response pairs. Additionally, we propose incorporating the data construction process into the fine-tuning data as code comprehension tasks, including instruction evolution, data filtering, and code review. Extensive experiments demonstrate that AlchemistCoder holds a clear lead among all models of the same size (6. 7B/7B) and rivals or even surpasses larger models (15B/33B/70B), showcasing the efficacy of our method in refining instruction-following capabilities and advancing the boundaries of code intelligence. Source code and models are available at https: //github. com/InternLM/AlchemistCoder.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models

  • Yuzhe Gu
  • Ziwei Ji
  • Wenwei Zhang
  • Chengqi Lyu
  • Dahua Lin
  • Kai Chen

Large language models (LLMs) exhibit hallucinations in long-form question-answering tasks across various domains and wide applications. Current hallucination detection and mitigation datasets are limited in domain and size, which struggle to scale due to prohibitive labor costs and insufficient reliability of existing hallucination annotators. To facilitate the scalable oversight of LLM hallucinations, this paper introduces an iterative self-training framework that simultaneously and progressively scales up the annotation dataset and improves the accuracy of the annotator. Based on the Expectation Maximization algorithm, in each iteration, the framework first applies an automatic hallucination annotation pipeline for a scaled dataset and then trains a more accurate annotator on the dataset. This new annotator is adopted in the annotation pipeline for the next iteration. Extensive experimental results demonstrate that the finally obtained hallucination annotator with only 7B parameters surpasses GPT-4 and obtains new state-of-the-art hallucination detection results on HaluEval and HalluQA by zero-shot inference. Such an annotator can not only evaluate the hallucination levels of various LLMs on the large-scale dataset but also help to mitigate the hallucination of LLMs generations, with the Natural Language Inference metric increasing from 25% to 37% on HaluEval.

PDF Details DOI

ICLR Conference 2024 Conference Paper

AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning

  • Yuwei Guo 0002
  • Ceyuan Yang
  • Anyi Rao
  • Zhengyang Liang
  • Yaohui Wang 0001
  • Yu Qiao 0001
  • Maneesh Agrawala
  • Dahua Lin

With the advance of text-to-image (T2I) diffusion models (e.g., Stable Diffusion) and corresponding personalization techniques such as DreamBooth and LoRA, everyone can manifest their imagination into high-quality images at an affordable cost. However, adding motion dynamics to existing high-quality personalized T2Is and enabling them to generate animations remains an open challenge. In this paper, we present AnimateDiff, a practical framework for animating personalized T2I models without requiring model-specific tuning. At the core of our framework is a plug-and-play motion module that can be trained once and seamlessly integrated into any personalized T2Is originating from the same base T2I. Through our proposed training strategy, the motion module effectively learns transferable motion priors from real-world videos. Once trained, the motion module can be inserted into a personalized T2I model to form a personalized animation generator. We further propose MotionLoRA, a lightweight fine-tuning technique for AnimateDiff that enables a pre-trained motion module to adapt to new motion patterns, such as different shot types, at a low training and data collection cost. We evaluate AnimateDiff and MotionLoRA on several public representative personalized T2I models collected from the community. The results demonstrate that our approaches help these models generate temporally smooth animation clips while preserving the visual quality and motion diversity. Codes and pre-trained weights are available at https://github.com/guoyww/AnimateDiff.

Details

NeurIPS Conference 2024 Conference Paper

Are We on the Right Way for Evaluating Large Vision-Language Models?

  • Lin Chen
  • Jinsong Li
  • Xiaoyi Dong
  • Pan Zhang
  • Yuhang Zang
  • Zehui Chen
  • Haodong Duan
  • Jiaqi Wang

Large vision-language models (LVLMs) have recently achieved rapid progress, sparking numerous studies to evaluate their multi-modal capabilities. However, we dig into current evaluation works and identify two primary issues: 1) Visual content is unnecessary for many samples. The answers can be directly inferred from the questions and options, or the world knowledge embedded in LLMs. This phenomenon is prevalent across current benchmarks. For instance, GeminiPro achieves 42. 7% on the MMMU benchmark without any visual input, and outperforms the random choice baseline across six benchmarks near 24% on average. 2) Unintentional data leakage exists in LLM and LVLM training. LLM and LVLM could still answer some visual-necessary questions without visual content, indicating the memorizing of these samples within large-scale training data. For example, Sphinx-X-MoE gets 43. 6% on MMMU without accessing images, surpassing its LLM backbone with 17. 9%. Both problems lead to misjudgments of actual multi-modal gains and potentially misguide the study of LVLM. To this end, we present MMStar, an elite vision-indispensable multi-modal benchmark comprising 1, 500 samples meticulously selected by humans. MMStar benchmarks 6 core capabilities and 18 detailed axes, aiming to evaluate LVLMs' multi-modal capacities with carefully balanced and purified samples. These samples are first roughly selected from current benchmarks with an automated pipeline, human review is then involved to ensure each curated sample exhibits visual dependency, minimal data leakage, and requires advanced multi-modal capabilities. Moreover, two metrics are developed to measure data leakage and actual performance gain in multi-modal training. We evaluate 16 leading LVLMs on MMStar to assess their multi-modal capabilities, and on 7 benchmarks with the proposed metrics to investigate their data leakage and actual multi-modal gain.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

CriticEval: Evaluating Large-scale Language Model as Critic

  • Tian Lan
  • Wenwei Zhang
  • Chen Xu
  • Heyan Huang
  • Dahua Lin
  • Kai Chen
  • Xian-Ling Mao

Critique ability, i. e. , the capability of Large Language Models (LLMs) to identify and rectify flaws in responses, is crucial for their applications in self-improvement and scalable oversight. While numerous studies have been proposed to evaluate critique ability of LLMs, their comprehensiveness and reliability are still limited. To overcome this problem, we introduce CriticEval, a novel benchmark designed to comprehensively and reliably evaluate critique ability of LLMs. Specifically, to ensure the comprehensiveness, CriticEval evaluates critique ability from four dimensions across nine diverse task scenarios. It evaluates both scalar-valued and textual critiques, targeting responses of varying quality. To ensure the reliability, a large number of critiques are annotated to serve as references, enabling GPT-4 to evaluate textual critiques reliably. Extensive evaluations of open-source and closed-source LLMs first validate the reliability of evaluation in CriticEval. Then, experimental results demonstrate the promising potential of open-source LLMs, the effectiveness of critique datasets and several intriguing relationships between the critique ability and some critical factors, including task types, response qualities and critique dimensions.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

FiVA: Fine-grained Visual Attribute Dataset for Text-to-Image Diffusion Models

  • Tong Wu
  • Yinghao Xu
  • Ryan Po
  • Mengchen Zhang
  • Guandao Yang
  • Jiaqi Wang
  • Ziwei Liu
  • Dahua Lin

Recent advances in text-to-image generation have enabled the creation of high-quality images with diverse applications. However, accurately describing desired visual attributes can be challenging, especially for non-experts in art and photography. An intuitive solution involves adopting favorable attributes from source images. Current methods attempt to distill identity and style from source images. However, "style" is a broad concept that includes texture, color, and artistic elements, but does not cover other important attributes like lighting and dynamics. Additionally, a simplified "style" adaptation prevents combining multiple attributes from different sources into one generated image. In this work, we formulate a more effective approach to decompose the aesthetics of a picture into specific visual attributes, letting users apply characteristics like lighting, texture, and dynamics from different images. To achieve this goal, we constructed the first fine-grained visual attributes dataset (FiVA) to the best of our knowledge. This FiVA dataset features a well-organized taxonomy for visual attributes and includes 1 M high-quality generated images with visual attribute annotations. Leveraging this dataset, we propose a fine-grained visual attributes adaptation framework (FiVA-Adapter), which decouples and adapts visual attributes from one or more source images into a generated one. This approach enhances user-friendly customization, allowing users to selectively apply desired attributes to create images that meet their unique preferences and specific content requirements.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation

  • Zhenzhi Wang
  • Yixuan Li
  • Yanhong Zeng
  • Youqing Fang
  • Yuwei Guo
  • Wenran Liu
  • Jing Tan
  • Kai Chen

Human image animation involves generating videos from a character photo, allowing user control and unlocking the potential for video and movie production. While recent approaches yield impressive results using high-quality training data, the inaccessibility of these datasets hampers fair and transparent benchmarking. Moreover, these approaches prioritize 2D human motion and overlook the significance of camera motions in videos, leading to limited control and unstable video generation. To demystify the training data, we present HumanVid, the first large-scale high-quality dataset tailored for human image animation, which combines crafted real-world and synthetic data. For the real-world data, we compile a vast collection of real-world videos from the internet. We developed and applied careful filtering rules to ensure video quality, resulting in a curated collection of 20K high-resolution (1080P) human-centric videos. Human and camera motion annotation is accomplished using a 2D pose estimator and a SLAM-based method. To expand our synthetic dataset, we collected 10K 3D avatar assets and leveraged existing assets of body shapes, skin textures and clothings. Notably, we introduce a rule-based camera trajectory generation method, enabling the synthetic pipeline to incorporate diverse and precise camera motion annotation, which can rarely be found in real-world data. To verify the effectiveness of HumanVid, we establish a baseline model named CamAnimate, short for Camera-controllable Human Animation, that considers both human and camera motions as conditions. Through extensive experimentation, we demonstrate that such simple baseline training on our HumanVid achieves state-of-the-art performance in controlling both human pose and camera motions, setting a new benchmark. Demo, data and code could be found in the project website: https: //humanvid. github. io/.

PDF Details DOI

ICLR Conference 2024 Conference Paper

HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion

  • Xian Liu
  • Jian Ren 0005
  • Aliaksandr Siarohin
  • Ivan Skorokhodov
  • Yanyu Li
  • Dahua Lin
  • Xihui Liu
  • Ziwei Liu 0002

Despite significant advances in large-scale text-to-image models, achieving hyper-realistic human image generation remains a desirable yet unsolved task. Existing models like Stable Diffusion and DALL·E 2 tend to generate human images with incoherent parts or unnatural poses. To tackle these challenges, our key insight is that human image is inherently structural over multiple granularities, from the coarse-level body skeleton to fine-grained spatial geometry. Therefore, capturing such correlations between the explicit appearance and latent structure in one model is essential to generate coherent and natural human images. To this end, we propose a unified framework, HyperHuman, that generates in-the-wild human images of high realism and diverse layouts. Specifically, 1) we first build a large-scale human-centric dataset, named HumanVerse, which consists of 340M images with comprehensive annotations like human pose, depth, and surface normal. 2) Next, we propose a Latent Structural Diffusion Model that simultaneously denoises the depth and surface normal along with the synthesized RGB image. Our model enforces the joint learning of image appearance, spatial relationship, and geometry in a unified network, where each branch in the model complements to each other with both structural awareness and textural richness. 3) Finally, to further boost the visual quality, we propose a Structure-Guided Refiner to compose the predicted conditions for more detailed generation of higher resolution. Extensive experiments demonstrate that our framework yields the state-of-the-art performance, generating hyper-realistic human images under diverse scenarios.

Details

NeurIPS Conference 2024 Conference Paper

InterControl: Zero-shot Human Interaction Generation by Controlling Every Joint

  • Zhenzhi Wang
  • Jingbo Wang
  • Yixuan Li
  • Dahua Lin
  • Bo Dai

Text-conditioned motion synthesis has made remarkable progress with the emergence of diffusion models. However, the majority of these motion diffusion models are primarily designed for a single character and overlook multi-human interactions. In our approach, we strive to explore this problem by synthesizing human motion with interactions for a group of characters of any size in a zero-shot manner. The key aspect of our approach is the adaptation of human-wise interactions as pairs of human joints that can be either in contact or separated by a desired distance. In contrast to existing methods that necessitate training motion generation models on multi-human motion datasets with a fixed number of characters, our approach inherently possesses the flexibility to model human interactions involving an arbitrary number of individuals, thereby transcending the limitations imposed by the training data. We introduce a novel controllable motion generation method, InterControl, to encourage the synthesized motions maintaining the desired distance between joint pairs. It consists of a motion controller and an inverse kinematics guidance module that realistically and accurately aligns the joints of synthesized characters to the desired location. Furthermore, we demonstrate that the distance between joint pairs for human-wise interactions can be generated using an off-the-shelf Large Language Model (LLM). Experimental results highlight the capability of our framework to generate interactions with multiple human characters and its potential to work with off-the-shelf physics-based character simulators. Code is available at https: //github. com/zhenzhiwang/intercontrol.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD

  • Xiaoyi Dong
  • Pan Zhang
  • Yuhang Zang
  • Yuhang Cao
  • Bin Wang
  • Linke Ouyang
  • Songyang Zhang
  • Haodong Duan

The Large Vision-Language Model (LVLM) field has seen significant advancements, yet its progression has been hindered by challenges in comprehending fine-grained visual content due to limited resolution. Recent efforts have aimed to enhance the high-resolution understanding capabilities of LVLMs, yet they remain capped at approximately 1500 $\times$ 1500 pixels and constrained to a relatively narrow resolution range. This paper represents InternLM-XComposer2-4KHD, a groundbreaking exploration into elevating LVLM resolution capabilities up to 4K HD (3840 × 1600) and beyond. Concurrently, considering the ultra-high resolution may not be necessary in all scenarios, it supports a wide range of diverse resolutions from 336 pixels to 4K standard, significantly broadening its scope of applicability. Specifically, this research advances the patch division paradigm by introducing a novel extension: dynamic resolution with automatic patch configuration. It maintains the training image aspect ratios while automatically varying patch counts and configuring layouts based on a pre-trained Vision Transformer (ViT) (336 $\times$ 336), leading to dynamic training resolution from 336 pixels to 4K standard. Our research demonstrates that scaling training resolution up to 4K HD leads to consistent performance enhancements without hitting the ceiling of potential improvements. InternLM-XComposer2-4KHD shows superb capability that matches or even surpasses GPT-4V and Gemini Pro in 10 of the 16 benchmarks.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Lean Workbook: A large-scale Lean problem set formalized from natural language math problems

  • Huaiyuan Ying
  • Zijian Wu
  • Yihan Geng
  • Jiayu Wang
  • Dahua Lin
  • Kai Chen

Large language models have demonstrated impressive capabilities across various natural language processing tasks, especially in solving mathematical problems. However, large language models are not good at math theorem proving using formal languages like Lean. A significant challenge in this area is the scarcity of training data available in these formal languages. To address this issue, we propose a novel pipeline that iteratively generates and filters synthetic data to translate natural language mathematical problems into Lean 4 statements, and vice versa. Our results indicate that the synthetic data pipeline can provide useful training data and improve the performance of LLMs in translating and understanding complex mathematical problems and proofs. Our final dataset contains about 57K formal-informal question pairs along with searched proof from the math contest forum and 21 new IMO questions. We open-source our code at \url{https: //github. com/InternLM/InternLM-Math} and our data at \url{https: //huggingface. co/datasets/InternLM/Lean-Workbook}.

PDF Details DOI

ICML Conference 2024 Conference Paper

Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback

  • Songyang Gao
  • Qiming Ge
  • Wei Shen
  • Shihan Dou
  • Junjie Ye 0005
  • Xiao Wang 0001
  • Rui Zheng
  • Yicheng Zou

The success of AI assistants based on Language Models (LLMs) hinges on Reinforcement Learning from Human Feedback (RLHF) to comprehend and align with user intentions. However, traditional alignment algorithms, such as PPO, are hampered by complex annotation and training requirements. This reliance limits the applicability of RLHF and hinders the development of professional assistants tailored to diverse human preferences. In this work, we introduce Linear Alignment, a novel algorithm that aligns language models with human preferences in one single inference step, eliminating the reliance on data annotation and model training. Linear alignment incorporates a new parameterization for policy optimization under divergence constraints, which enables the extraction of optimal policy in a closed-form manner and facilitates the direct estimation of the aligned response. Extensive experiments on both general and personalized preference datasets demonstrate that linear alignment significantly enhances the performance and efficiency of LLM alignment across diverse scenarios.

Details

NeurIPS Conference 2024 Conference Paper

Make-it-Real: Unleashing Large Multimodal Model for Painting 3D Objects with Realistic Materials

  • Ye Fang
  • Zeyi Sun
  • Tong Wu
  • Jiaqi Wang
  • Ziwei Liu
  • Gordon Wetzstein
  • Dahua Lin

Physically realistic materials are pivotal in augmenting the realism of 3D assets across various applications and lighting conditions. However, existing 3D assets and generative models often lack authentic material properties. Manual assignment of materials using graphic software is a tedious and time-consuming task. In this paper, we exploit advancements in Multimodal Large Language Models (MLLMs), particularly GPT-4V, to present a novel approach, Make-it-Real: 1) We demonstrate that GPT-4V can effectively recognize and describe materials, allowing the construction of a detailed material library. 2) Utilizing a combination of visual cues and hierarchical text prompts, GPT-4V precisely identifies and aligns materials with the corresponding components of 3D objects. 3) The correctly matched materials are then meticulously applied as reference for the new SVBRDF material generation according to the original albedo map, significantly enhancing their visual authenticity. Make-it-Real offers a streamlined integration into the 3D content creation workflow, showcasing its utility as an essential tool for developers of 3D assets.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

MGF: Mixed Gaussian Flow for Diverse Trajectory Prediction

  • Jiahe Chen
  • Jinkun Cao
  • Dahua Lin
  • Kris Kitani
  • Jiangmiao Pang

To predict future trajectories, the normalizing flow with a standard Gaussian prior suffers from weak diversity. The ineffectiveness comes from the conflict between the fact of asymmetric and multi-modal distribution of likely outcomes and symmetric and single-modal original distribution and supervision losses. Instead, we propose constructing a mixed Gaussian prior for a normalizing flow model for trajectory prediction. The prior is constructed by analyzing the trajectory patterns in the training samples without requiring extra annotations while showing better expressiveness and being multi-modal and asymmetric. Besides diversity, it also provides better controllability for probabilistic trajectory generation. We name our method Mixed Gaussian Flow (MGF). It achieves state-of-the-art performance in the evaluation of both trajectory alignment and diversity on the popular UCY/ETH and SDD datasets. Code is available at https: //github. com/mulplue/MGF.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding

  • Xinyu Fang
  • Kangrui Mao
  • Haodong Duan
  • Xiangyu Zhao
  • Yining Li
  • Dahua Lin
  • Kai Chen

The advent of large vision-language models (LVLMs) has spurred research into their applications in multi-modal contexts, particularly in video understanding. Traditional VideoQA benchmarks, despite providing quantitative metrics, often fail to encompass the full spectrum of video content and inadequately assess models' temporal comprehension. To address these limitations, we introduce MMBench-Video, a quantitative benchmark designed to rigorously evaluate LVLMs' proficiency in video understanding. MMBench-Video incorporates lengthy videos from YouTube and employs free-form questions, mirroring practical use cases. The benchmark is meticulously crafted to probe the models' temporal reasoning skills, with all questions human-annotated according to a carefully constructed ability taxonomy. We employ GPT-4 for automated assessment, demonstrating superior accuracy and robustness over earlier LLM-based evaluations. Utilizing MMBench-Video, we have conducted comprehensive evaluations that include both proprietary and open-source LVLMs for images and videos. MMBench-Video stands as a valuable resource for the research community, facilitating improved evaluation of LVLMs and catalyzing progress in the field of video understanding.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs

  • Ziyu Liu
  • Tao Chu
  • Yuhang Zang
  • Xilin Wei
  • Xiaoyi Dong
  • Pan Zhang
  • Zijian Liang
  • Yuanjun Xiong

Generating natural and meaningful responses to communicate with multi-modal human inputs is a fundamental capability of Large Vision-Language Models (LVLMs). While current open-source LVLMs demonstrate promising performance in simplified scenarios such as single-turn single-image input, they fall short in real-world conversation scenarios such as following instructions in a long context history with multi-turn and multi-images. Existing LVLM benchmarks primarily focus on single-choice questions or short-form responses, which do not adequately assess the capabilities of LVLMs in real-world human-AI interaction applications. Therefore, we introduce MMDU, a comprehensive benchmark, and MMDU-45k, a large-scale instruction tuning dataset, designed to evaluate and improve LVLMs' abilities in multi-turn and multi-image conversations. We employ the clustering algorithm to find the relevant images and textual descriptions from the open-source Wikipedia and construct the question-answer pairs by human annotators with the assistance of the GPT-4o model. MMDU has a maximum of 18k image+text tokens, 20 images, and 27 turns, which is at least 5x longer than previous benchmarks and poses challenges to current LVLMs. Our in-depth analysis of 15 representative LVLMs using MMDU reveals that open-source LVLMs lag behind closed-source counterparts due to limited conversational instruction tuning data. We demonstrate that fine-tuning open-source LVLMs on MMDU-45k significantly address this gap, generating longer and more accurate conversations, and improving scores on MMDU and existing benchmarks (MMStar: +1. 1%, MathVista: +1. 5%, ChartQA: +1. 2%). Our contributions pave the way for bridging the gap between current LVLM models and real-world application demands. The links to MMDU, and MMDU-45k are available in the supplementary material.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations

  • Ruiyuan Lyu
  • Jingli Lin
  • Tai WANG
  • Shuai Yang
  • Xiaohan Mao
  • Yilun Chen
  • Runsen Xu
  • Haifeng Huang

With the emergence of LLMs and their integration with other data modalities, multi-modal 3D perception attracts more attention due to its connectivity to the physical world and makes rapid progress. However, limited by existing datasets, previous works mainly focus on understanding object properties or inter-object spatial relationships in a 3D scene. To tackle this problem, this paper builds the first largest ever multi-modal 3D scene dataset and benchmark with hierarchical grounded language annotations, MMScan. It is constructed based on a top-down logic, from region to object level, from a single target to inter-target relationships, covering holistic aspects of spatial and attribute understanding. The overall pipeline incorporates powerful VLMs via carefully designed prompts to initialize the annotations efficiently and further involve humans' correction in the loop to ensure the annotations are natural, correct, and comprehensive. Built upon existing 3D scanning data, the resulting multi-modal 3D dataset encompasses 1. 4M meta-annotated captions on 109k objects and 7. 7k regions as well as over 3. 04M diverse samples for 3D visual grounding and question-answering benchmarks. We evaluate representative baselines on our benchmarks, analyze their capabilities in different aspects, and showcase the key problems to be addressed in the future. Furthermore, we use this high-quality dataset to train state-of-the-art 3D visual grounding and LLMs and obtain remarkable performance improvement both on existing benchmarks and in-the-wild evaluation.

PDF Details DOI

ICML Conference 2024 Conference Paper

MuxServe: Flexible Spatial-Temporal Multiplexing for Multiple LLM Serving

  • Jiangfei Duan
  • Runyu Lu
  • Haojie Duanmu
  • Xiuhong Li
  • Xingcheng Zhang
  • Dahua Lin
  • Ion Stoica
  • Hao Zhang 0025

Large language models (LLMs) have demonstrated remarkable performance, and organizations are racing to serve LLMs of varying sizes as endpoints for use-cases like chat, programming and search. However, efficiently serving multiple LLMs poses significant challenges for existing approaches due to varying popularity of LLMs. In the paper, we present MuxServe, a flexible spatial-temporal multiplexing system for efficient multiple LLM serving. The key insight behind is to colocate LLMs considering their popularity to multiplex memory resources, and leverage the characteristics of prefill and decoding phases to separate and flexibly colocate them to multiplex computation resources. MuxServe formally formulates the multiplexing problem, and proposes a novel placement algorithm and adaptive batch scheduling strategy to identify optimal colocations and maximize utilization. MuxServe designs a unified resource manager to enable flexible and efficient multiplexing. Evaluation results show that MuxServe can achieves up to $1. 8\times$ higher throughput or processes $2. 9\times$ more requests within $99%$ SLO attainment. The code is available at: https: //github. com/hao-ai-lab/MuxServe.

Details

NeurIPS Conference 2024 Conference Paper

OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI

  • Zhen Huang
  • Zengzhi Wang
  • Shijie Xia
  • Xuefeng Li
  • Haoyang Zou
  • Ruijie Xu
  • Run-Ze Fan
  • Lyumanshan Ye

The evolution of Artificial Intelligence (AI) has been significantly accelerated by advancements in Large Language Models (LLMs) and Large Multimodal Models (LMMs), gradually showcasing potential cognitive reasoning abilities in problem-solving and scientific discovery (i. e. , AI4Science) once exclusive to human intellect. To comprehensively evaluate current models' performance in cognitive reasoning abilities, we introduce OlympicArena, which includes 11, 163 bilingual problems across both text-only and interleaved text-image modalities. These challenges encompass a wide range of disciplines spanning seven fields and 62 international Olympic competitions, rigorously examined for data leakage. We argue that the challenges in Olympic competition problems are ideal for evaluating AI's cognitive reasoning due to their complexity and interdisciplinary nature, which are essential for tackling complex scientific challenges and facilitating discoveries. Beyond evaluating performance across various disciplines using answer-only criteria, we conduct detailed experiments and analyses from multiple perspectives. We delve into the models' cognitive reasoning abilities, their performance across different modalities, and their outcomes in process-level evaluations, which are vital for tasks requiring complex reasoning with lengthy solutions. Our extensive evaluations reveal that even advanced models like GPT-4o only achieve a 39. 97\% overall accuracy (28. 67\% for mathematics and 29. 71\% for physics), illustrating current AI limitations in complex reasoning and multimodal integration. Through the OlympicArena, we aim to advance AI towards superintelligence, equipping it to address more complex challenges in science and beyond. We also provide a comprehensive set of resources to support AI research, including a benchmark dataset, an open-source annotation platform, a detailed evaluation tool, and a leaderboard with automatic submission features.

PDF Details DOI

TMLR Journal 2024 Journal Article

PixMIM: Rethinking Pixel Reconstruction in Masked Image Modeling

  • Yuan Liu
  • Songyang Zhang
  • Jiacheng Chen
  • Kai Chen
  • Dahua Lin

Masked Image Modeling (MIM) has achieved promising progress with the advent of Masked Autoencoders (MAE) and BEiT. However, subsequent works have complicated the framework with new auxiliary tasks or extra pre-trained models, inevitably increasing computational overhead. This paper undertakes a fundamental analysis of MIM from the perspective of pixel reconstruction, which examines the input image patches and reconstruction target, and highlights two critical but previously overlooked bottlenecks. Based on this analysis, we propose a remarkably simple and effective method, PixMIM, that entails two strategies: 1) filtering the high-frequency components from the reconstruction target to de-emphasize the network's focus on texture-rich details and 2) adopting a conservative data transform strategy to alleviate the problem of missing foreground in MIM training. PixMIM can be easily integrated into most existing pixel-based MIM approaches (i.e., using raw images as reconstruction target) with negligible additional computation. Without bells and whistles, our method consistently improves four MIM approaches, MAE, MFF, ConvMAE, and LSMAE, across various downstream tasks. We believe this effective plug-and-play method will serve as a strong baseline for self-supervised learning and provide insights for future improvements of the MIM framework. Code and models will be available.

PDF Details

NeurIPS Conference 2024 Conference Paper

Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs

  • Yuxuan Qiao
  • Haodong Duan
  • Xinyu Fang
  • Junming Yang
  • Lin Chen
  • Songyang Zhang
  • Jiaqi Wang
  • Dahua Lin

Vision Language Models (VLMs) demonstrate remarkable proficiency in addressing a wide array of visual questions, which requires strong perception and reasoning faculties. Assessing these two competencies independently is crucial for model refinement, despite the inherent difficulty due to the intertwined nature of seeing and reasoning in existing VLMs. To tackle this issue, we present Prism, an innovative framework designed to disentangle the perception and reasoning processes involved in visual question solving. Prism comprises two distinct stages: a perception stage that utilizes a VLM to extract and articulate visual information in textual form, and a reasoning stage that formulates responses based on the extracted visual information using a Large Language Model (LLM). This modular design enables the systematic comparison and assessment of both proprietary and open-source VLM for their perception and reasoning strengths. Our analytical framework provides several valuable insights, underscoring Prism's potential as a cost-effective solution for vision-language tasks. By combining a streamlined VLM focused on perception with a powerful LLM tailored for reasoning, Prism achieves superior results in general vision-language tasks while substantially cutting down on training and operational expenses. Quantitative evaluations show that Prism, when configured with a vanilla 2B LLaVA and freely accessible GPT-3. 5, delivers performance on par with VLMs $10 \times$ larger on the rigorous multimodal benchmark MMStar.

PDF Details DOI

ICLR Conference 2024 Conference Paper

Scaling Laws of RoPE-based Extrapolation

  • Xiaoran Liu
  • Hang Yan 0001
  • Chenxin An
  • Xipeng Qiu
  • Dahua Lin

The extrapolation capability of Large Language Models (LLMs) based on Rotary Position Embedding \citep{su2021roformer} is currently a topic of considerable interest. The mainstream approach to addressing extrapolation with LLMs involves modifying RoPE by replacing 10000, the rotary base of $\theta_n={10000}^{-2n/d}$ in the original RoPE, with a larger value and providing longer fine-tuning text. In this work, we first observe that fine-tuning a RoPE-based LLM with either a smaller or larger base in pre-training context length could significantly enhance its extrapolation performance. After that, we propose \textbf{\textit{Scaling Laws of RoPE-based Extrapolation}}, a unified framework from the periodic perspective, to describe the relationship between the extrapolation performance and base value as well as tuning context length. In this process, we also explain the origin of the RoPE-based extrapolation issue by \textbf{\textit{critical dimension for extrapolation}}. Besides these observations and analyses, we achieve extrapolation up to 1 million context length within only 16K training length on LLaMA2 7B and 13B \citep{touvron2023llama2}.

Details

ICLR Conference 2024 Conference Paper

SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction

  • Xinyuan Chen
  • Yaohui Wang 0001
  • Lingjun Zhang
  • Shaobin Zhuang
  • Xin Ma 0031
  • Jiashuo Yu
  • Yali Wang 0001
  • Dahua Lin

Recently video generation has achieved substantial progress with realistic results. Nevertheless, existing AI-generated videos are usually very short clips ("shot-level'') depicting a single scene. To deliver a coherent long video ("story-level''), it is desirable to have creative transition and prediction effects across different clips. This paper presents a short-to-long video diffusion model, SEINE, that focuses on generative transition and prediction. The goal is to generate high-quality long videos with smooth and creative transitions between scenes and varying lengths of shot-level videos. Specifically, we propose a random-mask video diffusion model to automatically generate transitions based on textual descriptions. By providing the images of different scenes as inputs, combined with text-based control, our model generates transition videos that ensure coherence and visual quality. Furthermore, the model can be readily extended to various tasks such as image-to-video animation and autoregressive video prediction. To conduct a comprehensive evaluation of this new generative task, we propose three assessing criteria for smooth and creative transition: temporal consistency, semantic similarity, and video-text semantic alignment. Extensive experiments validate the effectiveness of our approach over existing methods for generative transition and prediction, enabling the creation of story-level long videos.

Details

NeurIPS Conference 2024 Conference Paper

ShareGPT4Video: Improving Video Understanding and Generation with Better Captions

  • Lin Chen
  • Xilin Wei
  • Jinsong Li
  • Xiaoyi Dong
  • Pan Zhang
  • Yuhang Zang
  • Zehui Chen
  • Haodong Duan

We present the ShareGPT4Video series, aiming to facilitate the video understanding of large video-language models (LVLMs) and the video generation of text-to-video models (T2VMs) via dense and precise captions. The series comprises: 1) ShareGPT4Video, 40K GPT4V annotated dense captions of videos with various lengths and sources, developed through carefully designed data filtering and annotating strategy. 2) ShareCaptioner-Video, an efficient and capable captioning model for arbitrary videos, with 4. 8M high-quality aesthetic videos annotated by it. 3) ShareGPT4Video-8B, a simple yet superb LVLM that reached SOTA performance on three advancing video benchmarks. To achieve this, taking aside the non-scalable costly human annotators, we find using GPT4V to caption video with a naive multi-frame or frame-concatenation input strategy leads to less detailed and sometimes temporal-confused results. We argue the challenge of designing a high-quality video captioning strategy lies in three aspects: 1) Inter-frame precise temporal change understanding. 2) Intra-frame detailed content description. 3) Frame-number scalability for arbitrary-length videos. To this end, we meticulously designed a differential video captioning strategy, which is stable, scalable, and efficient for generating captions for videos with arbitrary resolution, aspect ratios, and length. Based on it, we construct ShareGPT4Video, which contains 40K high-quality videos spanning a wide range of categories, and the resulting captions encompass rich world knowledge, object attributes, camera movements, and crucially, detailed and precise temporal descriptions of events. Based on ShareGPT4Video, we further develop ShareCaptioner-Video, a superior captioner capable of efficiently generating high-quality captions for arbitrary videos. We annotated 4. 8M aesthetically appealing videos by it and verified their effectiveness on a 10-second text2video generation task. For video understanding, we verified the effectiveness of ShareGPT4Video on several current LVLM architectures and presented our superb new LVLM ShareGPT4Video-8B. All the models, strategies, and annotations will be open-sourced and we hope this project can serve as a pivotal resource for advancing both the LVLMs and T2VMs community.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Streaming Long Video Understanding with Large Language Models

  • Rui Qian
  • Xiaoyi Dong
  • Pan Zhang
  • Yuhang Zang
  • Shuangrui Ding
  • Dahua Lin
  • Jiaqi Wang

This paper presents VideoStreaming, an advanced vision-language large model (VLLM) for video understanding, that capably understands arbitrary-length video with a constant number of video tokens streamingly encoded and adaptively selected. The challenge of video understanding in the vision language area mainly lies in the significant computational burden caused by the great number of tokens extracted from long videos. Previous works rely on sparse sampling or frame compression to reduce tokens. However, such approaches either disregard temporal information in a long time span or sacrifice spatial details, resulting in flawed compression. To address these limitations, our VideoStreaming has two core designs: Memory-Propagated Streaming Encoding and Adaptive Memory Selection. The Memory-Propagated Streaming Encoding architecture segments long videos into short clips and sequentially encodes each clip with a propagated memory. In each iteration, we utilize the encoded results of the preceding clip as historical memory, which is integrated with the current clip to distill a condensed representation that encapsulates the video content up to the current timestamp. This method not only incorporates long-term temporal dynamics into the streaming encoding process but also yields a fixed-length memory as a global representation for arbitrarily long videos. After the encoding process, the Adaptive Memory Selection strategy selects a constant number of question-related memories from all the historical memories, and feeds them into the LLM to generate informative responses. The question-related selection reduces redundancy within the memories, enabling efficient and precise video understanding. Meanwhile, the disentangled video extraction and reasoning design allows the LLM to answer different questions about a video by directly selecting corresponding memories, without the need to encode the whole video for each question. Through extensive experiments, our model achieves superior performance and higher efficiency on long video benchmarks, showcasing precise temporal comprehension for detailed question answering.

PDF Details DOI

ICLR Conference 2024 Conference Paper

Unified Human-Scene Interaction via Prompted Chain-of-Contacts

  • Zeqi Xiao
  • Tai Wang
  • Jingbo Wang 0003
  • Jinkun Cao
  • Wenwei Zhang
  • Bo Dai 0002
  • Dahua Lin
  • Jiangmiao Pang

Human-Scene Interaction (HSI) is a vital component of fields like embodied AI and virtual reality. Despite advancements in motion quality and physical plausibility, two pivotal factors, versatile interaction control and the development of a user-friendly interface, require further exploration before the practical application of HSI. This paper presents a unified HSI framework, UniHSI, which supports unified control of diverse interactions through language commands. The framework defines interaction as ``Chain of Contacts (CoC)", representing steps involving human joint-object part pairs. This concept is inspired by the strong correlation between interaction types and corresponding contact regions. Based on the definition, UniHSI constitutes a Large Language Model (LLM) Planner to translate language prompts into task plans in the form of CoC, and a Unified Controller that turns CoC into uniform task execution. To facilitate training and evaluation, we collect a new dataset named ScenePlan that encompasses thousands of task plans generated by LLMs based on diverse scenarios. Comprehensive experiments demonstrate the effectiveness of our framework in versatile task execution and generalizability to real scanned scenes.

Details

IROS Conference 2024 Conference Paper

X-neuron: Interpreting, Locating and Editing of Neurons in Reinforcement Learning Policy

  • Yuhong Ge
  • Xun Zhao
  • Jiangmiao Pang
  • Mingguo Zhao
  • Dahua Lin

Despite the impressive performance of Reinforcement Learning (RL), the black-box neural network backbone hinders users from trusting and deploying trained agents in real-world applications where safety is crucial. In order to make agents more trustworthy and controllable, for a given RL-trained policy, we propose to enhance its interpretability and make it human-controllable without retraining. We accomplish this goal by following a 3-step pipeline: 1) We interpret neurons by analyzing the causal effect of neurons on the kinematic attributes; To help agents unlock novel skills and enable human to assist agents in accomplishing tasks, 2) we locate the X-neuron, the optimal neuron that is capable of evoking the desired behavior; 3) and edit its activation values to achieve the precise control. We evaluate our method on various RL tasks ranging from autonomous driving to robot locomotion, and the results display that our approach outperforms previous work regarding almost all evaluation metrics. Through enhancing interpretability and introducing human control, the agents can improve safety and performance, even in unseen environments and novel tasks. For locomotion robots simply trained to walk forward, our method unlocks diverse controllable behaviors ranging from jump to backflip.

Details

IJCAI Conference 2023 Conference Paper

HireVAE: An Online and Adaptive Factor Model Based on Hierarchical and Regime-Switch VAE

  • Zikai Wei
  • Anyi Rao
  • Bo Dai
  • Dahua Lin

Factor model is a fundamental investment tool in quantitative investment, which can be empowered by deep learning to become more flexible and efficient in practical complicated investing situations. However, it is still an open question to build a factor model that can conduct stock prediction in an online and adaptive setting, where the model can adapt itself to match the current market regime identified based on only point-in-time market information. To tackle this problem, we propose the first deep learning based online and adaptive factor model, HireVAE, at the core of which is a hierarchical latent space that embeds the underlying relationship between the market situation and stock-wise latent factors, so that HireVAE can effectively estimate useful latent factors given only historical market information and subsequently predict accurate stock returns. Across four commonly used real stock market benchmarks, the proposed HireVAE demonstrate superior performance in terms of active returns over previous methods, verifying the potential of such online and adaptive factor model.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatars

  • Dongwei Pan
  • Long Zhuo
  • Jingtan Piao
  • Huiwen Luo
  • Wei Cheng
  • Yuxin Wang
  • Siming Fan
  • Shengqi Liu

Synthesizing high-fidelity head avatars is a central problem for computer vision and graphics. While head avatar synthesis algorithms have advanced rapidly, the best ones still face great obstacles in real-world scenarios. One of the vital causes is the inadequate datasets -- 1) current public datasets can only support researchers to explore high-fidelity head avatars in one or two task directions; 2) these datasets usually contain digital head assets with limited data volume, and narrow distribution over different attributes, such as expressions, ages, and accessories. In this paper, we present RenderMe-360, a comprehensive 4D human head dataset to drive advance in head avatar algorithms across different scenarios. It contains massive data assets, with 243+ million complete head frames and over 800k video sequences from 500 different identities captured by multi-view cameras at 30 FPS. It is a large-scale digital library for head avatars with three key attributes: 1) High Fidelity: all subjects are captured in 360 degrees via 60 synchronized, high-resolution 2K cameras. 2) High Diversity: The collected subjects vary from different ages, eras, ethnicities, and cultures, providing abundant materials with distinctive styles in appearance and geometry. Moreover, each subject is asked to perform various dynamic motions, such as expressions and head rotations, which further extend the richness of assets. 3) Rich Annotations: the dataset provides annotations with different granularities: cameras' parameters, background matting, scan, 2D/3D facial landmarks, FLAME fitting, and text description. Based on the dataset, we build a comprehensive benchmark for head avatar research, with 16 state-of-the-art methods performed on five main tasks: novel view synthesis, novel expression synthesis, hair rendering, hair editing, and talking head generation. Our experiments uncover the strengths and flaws of state-of-the-art methods. RenderMe-360 opens the door for future exploration in modern head avatars. All of the data, code, and models will be publicly available at https: //renderme-360. github. io/.

PDF Details

ICLR Conference 2023 Conference Paper

Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction

  • Tong Wu
  • Jiaqi Wang 0003
  • Xingang Pan
  • Xudong Xu
  • Christian Theobalt
  • Ziwei Liu 0002
  • Dahua Lin

Neural surface reconstruction aims to reconstruct accurate 3D surfaces based on multi-view images. Previous methods based on neural volume rendering mostly train a fully implicit model with MLPs, which typically require hours of training for a single scene. Recent efforts explore the explicit volumetric representation to accelerate the optimization via memorizing significant information with learnable voxel grids. However, existing voxel-based methods often struggle in reconstructing fine-grained geometry, even when combined with an SDF-based volume rendering scheme. We reveal that this is because 1) the voxel grids tend to break the color-geometry dependency that facilitates fine-geometry learning, and 2) the under-constrained voxel grids lack spatial coherence and are vulnerable to local minima. In this work, we present Voxurf, a voxel-based surface reconstruction approach that is both efficient and accurate. Voxurf addresses the aforementioned issues via several key designs, including 1) a two-stage training procedure that attains a coherent coarse shape and recovers fine details successively, 2) a dual color network that maintains color-geometry dependency, and 3) a hierarchical geometry feature to encourage information propagation across voxels. Extensive experiments show that Voxurf achieves high efficiency and high quality at the same time. On the DTU benchmark, Voxurf achieves higher reconstruction quality with a 20x training speedup compared to previous fully implicit methods. Our code is publicly available at https://github.com/wutong16/Voxurf/.

Details

ICLR Conference 2022 Conference Paper

A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion

  • Zhaoyang Lyu
  • Zhifeng Kong
  • Xudong Xu
  • Liang Pan
  • Dahua Lin

3D point clouds are an important data format that captures 3D information for real world objects. Since 3D point clouds scanned in the real world are often incomplete, it is important to recover the complete point cloud for many downstreaming applications. Most existing point cloud completion methods use the Chamfer Distance (CD) loss for training. The CD loss estimates correspondences between two point clouds by searching nearest neighbors, which does not capture the overall point distribution on the generated shape, and therefore likely leads to non-uniform point cloud generation. To tackle this problem, we propose a novel Point Diffusion-Refinement (PDR) paradigm for point cloud completion. PDR consists of a Conditional Generation Network (CGNet) and a ReFinement Network (RFNet). The CGNet uses a conditional generative model called the denoising diffusion probabilistic model (DDPM) to generate a coarse completion conditioned on the partial observation. DDPM establishes a one-to-one pointwise mapping between the generated point cloud and the uniform ground truth, and then optimizes the mean squared error loss to realize uniform generation. The RFNet refines the coarse output of the CGNet and further improves quality of the completed point cloud. In terms of the architecture, we develop a novel dual-path architecture for both networks. The architecture can (1) effectively and efficiently extract multi-level features from partially observed point clouds to guide completion, and (2) accurately manipulate spatial locations of 3D points to obtain smooth surfaces and sharp details. Extensive experimental results on various benchmark datasets show that our PDR paradigm outperforms previous state-of-the-art methods for point cloud completion. In addition, with the help of the RFNet, we can accelerate the iterative generation process of the DDPM by up to 50 times without much performance drop.

Details

NeurIPS Conference 2022 Conference Paper

Audio-Driven Co-Speech Gesture Video Generation

  • Xian Liu
  • Qianyi Wu
  • Hang Zhou
  • Yuanqi Du
  • Wayne Wu
  • Dahua Lin
  • Ziwei Liu

Co-speech gesture is crucial for human-machine interaction and digital entertainment. While previous works mostly map speech audio to human skeletons (e. g. , 2D keypoints), directly generating speakers' gestures in the image domain remains unsolved. In this work, we formally define and study this challenging problem of audio-driven co-speech gesture video generation, i. e. , using a unified framework to generate speaker image sequence driven by speech audio. Our key insight is that the co-speech gestures can be decomposed into common motion patterns and subtle rhythmic dynamics. To this end, we propose a novel framework, Audio-driveN Gesture vIdeo gEneration (ANGIE), to effectively capture the reusable co-speech gesture patterns as well as fine-grained rhythmic movements. To achieve high-fidelity image sequence generation, we leverage an unsupervised motion representation instead of a structural human body prior (e. g. , 2D skeletons). Specifically, 1) we propose a vector quantized motion extractor (VQ-Motion Extractor) to summarize common co-speech gesture patterns from implicit motion representation to codebooks. 2) Moreover, a co-speech gesture GPT with motion refinement (Co-Speech GPT) is devised to complement the subtle prosodic motion details. Extensive experiments demonstrate that our framework renders realistic and vivid co-speech gesture video. Demo video and more resources can be found in: https: //alvinliu0. github. io/projects/ANGIE

PDF Details

NeurIPS Conference 2022 Conference Paper

Semi-Supervised Semantic Segmentation via Gentle Teaching Assistant

  • Ying Jin
  • Jiaqi Wang
  • Dahua Lin

Semi-Supervised Semantic Segmentation aims at training the segmentation model with limited labeled data and a large amount of unlabeled data. To effectively leverage the unlabeled data, pseudo labeling, along with the teacher-student framework, is widely adopted in semi-supervised semantic segmentation. Though proved to be effective, this paradigm suffers from incorrect pseudo labels which inevitably exist and are taken as auxiliary training data. To alleviate the negative impact of incorrect pseudo labels, we delve into the current Semi-Supervised Semantic Segmentation frameworks. We argue that the unlabeled data with pseudo labels can facilitate the learning of representative features in the feature extractor, but it is unreliable to supervise the mask predictor. Motivated by this consideration, we propose a novel framework, Gentle Teaching Assistant (GTA-Seg) to disentangle the effects of pseudo labels on feature extractor and mask predictor of the student model. Specifically, in addition to the original teacher-student framework, our method introduces a teaching assistant network which directly learns from pseudo labels generated by the teacher network. The gentle teaching assistant (GTA) is coined gentle since it only transfers the beneficial feature representation knowledge in the feature extractor to the student model in an Exponential Moving Average (EMA) manner, protecting the student model from the negative influences caused by unreliable pseudo labels in the mask predictor. The student model is also supervised by reliable labeled data to train an accurate mask predictor, further facilitating feature representation. Extensive experiment results on benchmark datasets validate that our method shows competitive performance against previous methods. We promise to release our code towards reproducibility.

PDF Details

NeurIPS Conference 2021 Conference Paper

Balanced Chamfer Distance as a Comprehensive Metric for Point Cloud Completion

  • Tong Wu
  • Liang Pan
  • Junzhe Zhang
  • Tai WANG
  • Ziwei Liu
  • Dahua Lin

Chamfer Distance (CD) and Earth Mover’s Distance (EMD) are two broadly adopted metrics for measuring the similarity between two point sets. However, CD is usually insensitive to mismatched local density, and EMD is usually dominated by global distribution while overlooks the fidelity of detailed structures. Besides, their unbounded value range induces a heavy influence from the outliers. These defects prevent them from providing a consistent evaluation. To tackle these problems, we propose a new similarity measure named Density-aware Chamfer Distance (DCD). It is derived from CD and benefits from several desirable properties: 1) it can detect disparity of density distributions and is thus a more intensive measure of similarity compared to CD; 2) it is stricter with detailed structures and significantly more computationally efficient than EMD; 3) the bounded value range encourages a more stable and reasonable evaluation over the whole test set. We adopt DCD to evaluate the point cloud completion task, where experimental results show that DCD pays attention to both the overall structure and local geometric details and provides a more reliable evaluation even when CD and EMD contradict each other. We can also use DCD as the training loss, which outperforms the same model trained with CD loss on all three metrics. In addition, we propose a novel point discriminator module that estimates the priority for another guided down-sampling step, and it achieves noticeable improvements under DCD together with competitive results for both CD and EMD. We hope our work could pave the way for a more comprehensive and practical point cloud similarity evaluation. Our code will be available at https: //github. com/wutong16/Density aware Chamfer_Distance.

PDF Details

NeurIPS Conference 2021 Conference Paper

Few-Shot Object Detection via Association and DIscrimination

  • Yuhang Cao
  • Jiaqi Wang
  • Ying Jin
  • Tong Wu
  • Kai Chen
  • Ziwei Liu
  • Dahua Lin

Object detection has achieved substantial progress in the last decade. However, detecting novel classes with only few samples remains challenging, since deep learning under low data regime usually leads to a degraded feature space. Existing works employ a holistic fine-tuning paradigm to tackle this problem, where the model is first pre-trained on all base classes with abundant samples, and then it is used to carve the novel class feature space. Nonetheless, this paradigm is still imperfect. Durning fine-tuning, a novel class may implicitly leverage the knowledge of multiple base classes to construct its feature space, which induces a scattered feature space, hence violating the inter-class separability. To overcome these obstacles, we propose a two-step fine-tuning framework, Few-shot object detection via Association and DIscrimination (FADI), which builds up a discriminative feature space for each novel class with two integral steps. 1) In the association step, in contrast to implicitly leveraging multiple base classes, we construct a compact novel class feature space via explicitly imitating a specific base class feature space. Specifically, we associate each novel class with a base class according to their semantic similarity. After that, the feature space of a novel class can readily imitate the well-trained feature space of the associated base class. 2) In the discrimination step, to ensure the separability between the novel classes and associated base classes, we disentangle the classification branches for base and novel classes. To further enlarge the inter-class separability between all classes, a set-specialized margin loss is imposed. Extensive experiments on standard Pascal VOC and MS-COCO datasets demonstrate that FADI achieves new state-of-the-art performance, significantly improving the baseline in any shot/split by +18. 7. Notably, the advantage of FADI is most announced on extremely few-shot scenarios (e. g. 1- and 3- shot).

PDF Details

NeurIPS Conference 2021 Conference Paper

Generative Occupancy Fields for 3D Surface-Aware Image Synthesis

  • Xudong XU
  • Xingang Pan
  • Dahua Lin
  • Bo Dai

The advent of generative radiance fields has significantly promoted the development of 3D-aware image synthesis. The cumulative rendering process in radiance fields makes training these generative models much easier since gradients are distributed over the entire volume, but leads to diffused object surfaces. In the meantime, compared to radiance fields occupancy representations could inherently ensure deterministic surfaces. However, if we directly apply occupancy representations to generative models, during training they will only receive sparse gradients located on object surfaces and eventually suffer from the convergence problem. In this paper, we propose Generative Occupancy Fields (GOF), a novel model based on generative radiance fields that can learn compact object surfaces without impeding its training convergence. The key insight of GOF is a dedicated transition from the cumulative rendering in radiance fields to rendering with only the surface points as the learned surface gets more and more accurate. In this way, GOF combines the merits of two representations in a unified framework. In practice, the training-time transition of start from radiance fields and march to occupancy representations is achieved in GOF by gradually shrinking the sampling region in its rendering process from the entire volume to a minimal neighboring region around the surface. Through comprehensive experiments on multiple datasets, we demonstrate that GOF can synthesize high-quality images with 3D consistency and simultaneously learn compact and smooth object surfaces. Our code is available at https: //github. com/SheldonTsui/GOF_NeurIPS2021.

PDF Details

AAAI Conference 2021 Conference Paper

Joint Semantic-geometric Learning for Polygonal Building Segmentation

  • Weijia Li
  • Wenqian Zhao
  • Huaping Zhong
  • Conghui He
  • Dahua Lin

Building extraction from aerial or satellite images has been an important research problem in remote sensing and computer vision domains for decades. Compared with pixel-wise semantic segmentation models that output raster building segmentation map, polygonal building segmentation approaches produce more realistic building polygons that are in the desirable vector format for practical applications. Despite the substantial efforts over recent years, state-of-the-art polygonal building segmentation methods still suffer from several limitations, e. g. , (1) relying on a perfect segmentation map to guarantee the vectorization quality; (2) requiring a complex post-processing procedure; (3) generating inaccurate vertices with a fixed quantity, a wrong sequential order, self-intersections, etc. To tackle the above issues, in this paper, we propose a polygonal building segmentation approach and make the following contributions: (1) We design a multitask segmentation network for joint semantic and geometric learning via three tasks, i. e. , pixel-wise building segmentation, multi-class corner prediction, and edge orientation prediction. (2) We propose a simple but effective vertex generation module for transforming the segmentation contour into high-quality polygon vertices. (3) We further propose a polygon refinement network that automatically moves the polygon vertices into more accurate locations. Results on two popular building segmentation datasets demonstrate that our approach achieves significant improvements for both building instance segmentation (with 2% F1-score gain) and polygon vertex prediction (with 6% F1-score gain) compared with current state-of-the-art methods.

PDF Details

AAAI Conference 2021 Conference Paper

Temporal ROI Align for Video Object Recognition

  • Tao Gong
  • Kai Chen
  • Xinjiang Wang
  • Qi Chu
  • Feng Zhu
  • Dahua Lin
  • Nenghai Yu
  • Huamin Feng

Video object detection is challenging in the presence of appearance deterioration in certain video frames. Therefore, it is a natural choice to aggregate temporal information from other frames of the same video into the current frame. However, ROI Align, as one of the most core procedures of video detectors, still remains extracting features from a single-frame feature map for proposals, making the extracted ROI features lack temporal information from videos. In this work, considering the features of the same object instance are highly similar among frames in a video, a novel Temporal ROI Align operator is proposed to extract features from other frames feature maps for current frame proposals by utilizing feature similarity. The proposed Temporal ROI Align operator can extract temporal information from the entire video for proposals. We integrate it into single-frame video detectors and other state-of-the-art video detectors, and conduct quantitative experiments to demonstrate that the proposed Temporal ROI Align operator can consistently and significantly boost the performance. Besides, the proposed Temporal ROI Align can also be applied into video instance segmentation.

PDF Details

AAAI Conference 2020 Conference Paper

Fastened CROWN: Tightened Neural Network Robustness Certificates

  • Zhaoyang Lyu
  • Ching-Yun Ko
  • Zhifeng Kong
  • Ngai Wong
  • Dahua Lin
  • Luca Daniel

The rapid growth of deep learning applications in real life is accompanied by severe safety concerns. To mitigate this uneasy phenomenon, much research has been done providing reliable evaluations of the fragility level in different deep neural networks. Apart from devising adversarial attacks, quanti- fiers that certify safeguarded regions have also been designed in the past five years. The summarizing work in (Salman et al. 2019) unifies a family of existing verifiers under a convex relaxation framework. We draw inspiration from such work and further demonstrate the optimality of deterministic CROWN (Zhang et al. 2018) solutions in a given linear programming problem under mild constraints. Given this theoretical result, the computationally expensive linear programming based method is shown to be unnecessary. We then propose an optimization-based approach FROWN (Fastened CROWN): a general algorithm to tighten robustness certificates for neural networks. Extensive experiments on various networks trained individually verify the effectiveness of FROWN in safeguarding larger robust regions.

PDF Details

ICLR Conference 2020 Conference Paper

Real or Not Real, that is the Question

  • Yuanbo Xiangli
  • Yubin Deng
  • Bo Dai 0002
  • Chen Change Loy
  • Dahua Lin

While generative adversarial networks (GAN) have been widely adopted in various topics, in this paper we generalize the standard GAN to a new perspective by treating realness as a random variable that can be estimated from multiple angles. In this generalized framework, referred to as RealnessGAN, the discriminator outputs a distribution as the measure of realness. While RealnessGAN shares similar theoretical guarantees with the standard GAN, it provides more insights on adversarial learning. More importantly, compared to multiple baselines, RealnessGAN provides stronger guidance for the generator, achieving improvements on both synthetic and real-world datasets. Moreover, it enables the basic DCGAN architecture to generate realistic images at 1024*1024 resolution when trained from scratch.

Details

NeurIPS Conference 2019 Conference Paper

Policy Continuation with Hindsight Inverse Dynamics

  • Hao Sun
  • Zhizhong Li
  • Xiaotong Liu
  • Bolei Zhou
  • Dahua Lin

Solving goal-oriented tasks is an important but challenging problem in reinforcement learning (RL). For such tasks, the rewards are often sparse, making it difficult to learn a policy effectively. To tackle this difficulty, we propose a new approach called Policy Continuation with Hindsight Inverse Dynamics (PCHID). This approach learns from Hindsight Inverse Dynamics based on Hindsight Experience Replay. Enabling the learning process in a self-imitated manner and thus can be trained with supervised learning. This work also extends it to multi-step settings with Policy Continuation. The proposed method is general, which can work in isolation or be combined with other on-policy and off-policy algorithms. On two multi-goal tasks GridWorld and FetchReach, PCHID significantly improves the sample efficiency as well as the final performance.

PDF Details

ICML Conference 2019 Conference Paper

POPQORN: Quantifying Robustness of Recurrent Neural Networks

  • Ching-Yun Ko
  • Zhaoyang Lyu
  • Lily Weng
  • Luca Daniel
  • Ngai Wong 0001
  • Dahua Lin

The vulnerability to adversarial attacks has been a critical issue for deep neural networks. Addressing this issue requires a reliable way to evaluate the robustness of a network. Recently, several methods have been developed to compute robustness quantification for neural networks, namely, certified lower bounds of the minimum adversarial perturbation. Such methods, however, were devised for feed-forward networks, e. g. multi-layer perceptron or convolutional networks. It remains an open problem to quantify robustness for recurrent networks, especially LSTM and GRU. For such networks, there exist additional challenges in computing the robustness quantification, such as handling the inputs at multiple steps and the interaction between gates and states. In this work, we propose POPQORN (Propagated-output Quantified Robustness for RNNs), a general algorithm to quantify robustness of RNNs, including vanilla RNNs, LSTMs, and GRUs. We demonstrate its effectiveness on different network architectures and show that the robustness quantification on individual steps can lead to new insights.

Details

NeurIPS Conference 2018 Conference Paper

A Neural Compositional Paradigm for Image Captioning

  • Bo Dai
  • Sanja Fidler
  • Dahua Lin

Mainstream captioning models often follow a sequential structure to generate cap- tions, leading to issues such as introduction of irrelevant semantics, lack of diversity in the generated captions, and inadequate generalization performance. In this paper, we present an alternative paradigm for image captioning, which factorizes the captioning procedure into two stages: (1) extracting an explicit semantic representation from the given image; and (2) constructing the caption based on a recursive compositional procedure in a bottom-up manner. Compared to conventional ones, our paradigm better preserves the semantic content through an explicit factorization of semantics and syntax. By using the compositional generation procedure, caption construction follows a recursive structure, which naturally fits the properties of human language. Moreover, the proposed compositional procedure requires less data to train, generalizes better, and yields more diverse captions.

PDF Details

AAAI Conference 2018 Conference Paper

Accelerated Training for Massive Classification via Dynamic Class Selection

  • Xingcheng Zhang
  • Lei Yang
  • Junjie Yan
  • Dahua Lin

Massive classification, a classification task defined over a vast number of classes (hundreds of thousands or even millions), has become an essential part of many real-world systems, such as face recognition. Existing methods, including the deep networks that achieved remarkable success in recent years, were mostly devised for problems with a moderate number of classes. They would meet with substantial difficulties, e. g. excessive memory demand and computational cost, when applied to massive problems. We present a new method to tackle this problem. This method can efficiently and accurately identify a small number of “active classes” for each mini-batch, based on a set of dynamic class hierarchies constructed on the fly. We also develop an adaptive allocation scheme thereon, which leads to a better tradeoff between performance and cost. On several large-scale benchmarks, our method significantly reduces the training cost and memory demand, while maintaining competitive performance.

PDF Details

AAAI Conference 2018 Conference Paper

Probabilistic Ensemble of Collaborative Filters

  • Zhiyu Min
  • Dahua Lin

Collaborative filtering is an important technique for recommendation. Whereas it has been repeatedly shown to be effective in previous work, its performance remains unsatisfactory in many real-world applications, especially those where the items or users are highly diverse. In this paper, we explore an ensemble-based framework to enhance the capability of a recommender in handling diverse data. Specifically, we formulate a probabilistic model which integrates the items, the users, as well as the associations between them into a generative process. On top of this formulation, we further derive a progressive algorithm to construct an ensemble of collaborative filters. In each iteration, a new filter is derived from re-weighted entries and incorporated into the ensemble. It is noteworthy that while the algorithmic procedure of our algorithm is apparently similar to boosting, it is derived from an essentially different formulation and thus differs in several key technical aspects. We tested the proposed method on three large datasets, and observed substantial improvement over the state of the art, including L2Boost, an effective method based on boosting.

PDF Details

AAAI Conference 2018 Conference Paper

Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition

  • Sijie Yan
  • Yuanjun Xiong
  • Dahua Lin

Dynamics of human body skeletons convey significant information for human action recognition. Conventional approaches for modeling skeletons usually rely on hand-crafted parts or traversal rules, thus resulting in limited expressive power and difficulties of generalization. In this work, we propose a novel model of dynamic skeletons called Spatial- Temporal Graph Convolutional Networks (ST-GCN), which moves beyond the limitations of previous methods by automatically learning both the spatial and temporal patterns from data. This formulation not only leads to greater expressive power but also stronger generalization capability. On two large datasets, Kinetics and NTU-RGBD, it achieves substantial improvements over mainstream methods.

PDF Details

NeurIPS Conference 2018 Conference Paper

Trajectory Convolution for Action Recognition

  • Yue Zhao
  • Yuanjun Xiong
  • Dahua Lin

How to leverage the temporal dimension is a key question in video analysis. Recent works suggest an efficient approach to video feature learning, i. e. , factorizing 3D convolutions into separate components respectively for spatial and temporal convolutions. The temporal convolution, however, comes with an implicit assumption – the feature maps across time steps are well aligned so that the features at the same locations can be aggregated. This assumption may be overly strong in practical applications, especially in action recognition where the motion serves as a crucial cue. In this work, we propose a new CNN architecture TrajectoryNet, which incorporates trajectory convolution, a new operation for integrating features along the temporal dimension, to replace the existing temporal convolution. This operation explicitly takes into account the changes in contents caused by deformation or motion, allowing the visual features to be aggregated along the the motion paths, trajectories. On two large-scale action recognition datasets, namely, Something-Something and Kinetics, the proposed network architecture achieves notable improvement over strong baselines.

PDF Details

NeurIPS Conference 2017 Conference Paper

Contrastive Learning for Image Captioning

  • Bo Dai
  • Dahua Lin

Image captioning, a popular topic in computer vision, has achieved substantial progress in recent years. However, the distinctiveness of natural descriptions is often overlooked in previous work. It is closely related to the quality of captions, as distinctive captions are more likely to describe images with their unique aspects. In this work, we propose a new learning method, Contrastive Learning (CL), for image captioning. Specifically, via two constraints formulated on top of a reference model, the proposed method can encourage distinctiveness, while maintaining the overall quality of the generated captions. We tested our method on two challenging datasets, where it improves the baseline model by significant margins. We also showed in our studies that the proposed method is generic and can be used for models with various structures.

PDF Details

IJCAI Conference 2017 Conference Paper

Integrating Specialized Classifiers Based on Continuous Time Markov Chain

  • Zhizhong Li
  • Dahua Lin

Specialized classifiers, namely those dedicated to a subset of classes, are often adopted in real-world recognition systems. However, integrating such classifiers is nontrivial. Existing methods, e. g. weighted average, usually implicitly assume that all constituents of an ensemble cover the same set of classes. Such methods can produce misleading predictions when used to combine specialized classifiers. This work explores a novel approach. Instead of combining predictions from individual classifiers directly, it first decomposes the predictions into sets of pairwise preferences, treating them as transition channels between classes, and thereon constructs a continuous-time Markov chain, and use the equilibrium distribution of this chain as the final prediction. This way allows us to form a coherent picture over all specialized predictions. On large public datasets, the proposed method obtains considerable improvement compared to mainstream ensemble methods, especially when the classifier coverage is highly unbalanced.

PDF Details

IJCAI Conference 2017 Conference Paper

Scalable Estimation of Dirichlet Process Mixture Models on Distributed Data

  • Ruohui Wang
  • Dahua Lin

We consider the estimation of Dirichlet Process Mixture Models (DPMMs) in distributed environments, where data are distributed across multiple computing nodes. A key advantage of Bayesian nonparametric models such as DPMMs is that they allow new components to be introduced on the fly as needed. This, however, posts an important challenge to distributed estimation -- how to handle new components efficiently and consistently. To tackle this problem, we propose a new estimation method, which allows new components to be created locally in individual computing nodes. Components corresponding to the same cluster will be identified and merged via a probabilistic consolidation scheme. In this way, we can maintain the consistency of estimation with very low communication cost. Experiments on large real-world data sets show that the proposed method can achieve high scalability in distributed and asynchronous environments without compromising the mixing performance.

PDF Details

NeurIPS Conference 2013 Conference Paper

Online Learning of Nonparametric Mixture Models via Sequential Variational Approximation

  • Dahua Lin

Reliance on computationally expensive algorithms for inference has been limiting the use of Bayesian nonparametric models in large scale applications. To tackle this problem, we propose a Bayesian learning algorithm for DP mixture models. Instead of following the conventional paradigm -- random initialization plus iterative update, we take an progressive approach. Starting with a given prior, our method recursively transforms it into an approximate posterior through sequential variational approximation. In this process, new components will be incorporated on the fly when needed. The algorithm can reliably estimate a DP mixture model in one pass, making it particularly suited for applications with massive data. Experiments on both synthetic data and real datasets demonstrate remarkable improvement on efficiency -- orders of magnitude speed-up compared to the state-of-the-art.

PDF Details

NeurIPS Conference 2012 Conference Paper

Coupling Nonparametric Mixtures via Latent Dirichlet Processes

  • Dahua Lin
  • John Fisher

Mixture distributions are often used to model complex data. In this paper, we develop a new method that jointly estimates mixture models over multiple data sets by exploiting the statistical dependencies between them. Specifically, we introduce a set of latent Dirichlet processes as sources of component models (atoms), and for each data set, we construct a nonparametric mixture model by combining sub-sampled versions of the latent DPs. Each mixture model may acquire atoms from different latent DPs, while each atom may be shared by multiple mixtures. This multi-to-multi association distinguishes the proposed method from prior constructions that rely on tree or chain structures, allowing mixture models to be coupled more flexibly. In addition, we derive a sampling algorithm that jointly infers the model parameters and present experiments on both document analysis and image modeling.

PDF Details

NeurIPS Conference 2010 Conference Paper

Construction of Dependent Dirichlet Processes based on Poisson Processes

  • Dahua Lin
  • Eric Grimson
  • John Fisher

We present a novel method for constructing dependent Dirichlet processes. The approach exploits the intrinsic relationship between Dirichlet and Poisson pro- cesses in order to create a Markov chain of Dirichlet processes suitable for use as a prior over evolving mixture models. The method allows for the creation, re- moval, and location variation of component models over time while maintaining the property that the random measures are marginally DP distributed. Addition- ally, we derive a Gibbs sampling algorithm for model inference and test it on both synthetic and real data. Empirical results demonstrate that the approach is effec- tive in estimating dynamically varying mixture models.

PDF Details