Dahua Lin

Venues

Frequent coauthors

Papers

1. Half-S: Halving the Scale for Near-Lossless 4-Bit LLM Training
   ACL 2026 ·

   Jinyang Du

   DBLP profile ↗ORCID search ↗
2. MathSmith: Towards Extremely Hard Mathematical Reasoning by Forging Synthetic Problems with a Reinforced Policy
   AAAI 2026 ·

   Shaoxiong Zhan

   DBLP profile ↗ORCID search ↗
3. MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing
   ACL 2026 ·

   Junbo Niu

   DBLP profile ↗ORCID search ↗
4. Timely Machine: Awareness of Time Makes Test-Time Scaling Agentic
   ACL 2026 ·

   Yichuan Ma

   DBLP profile ↗ORCID search ↗
5. Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling
   AAAI 2026 ·

   Hao Li

   DBLP profile ↗ORCID search ↗
6. Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs
   ACL 2026 ·

   Yu Li

   DBLP profile ↗ORCID search ↗
7. 3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion
   CVPR 2025 ·

   Zhaoxi Chen

   DBLP profile ↗ORCID search ↗
8. 3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation
   ICLR 2025 ·

   Xiao Fu

   DBLP profile ↗ORCID search ↗
9. Bootstrap3D: Improving Multi-View Diffusion Model with Synthetic Data
   ICCV 2025 ·

   Zeyi Sun

   DBLP profile ↗ORCID search ↗
10. ByTheWay: Boost Your Text-to-Video Generation Model to Higher Quality in a Training-free Way
    CVPR 2025 ·

    Jiazi Bu

    DBLP profile ↗ORCID search ↗
11. Conical Visual Concentration for Efficient Large Vision-Language Models
    CVPR 2025 ·

    Long Xing

    DBLP profile ↗ORCID search ↗
12. Consultant Decoding: Yet Another Synergistic Mechanism
    ACL 2025 ·

    Chuanghao Ding

    DBLP profile ↗ORCID search ↗
13. Creation-Mmbench: Assessing Context-Aware Creative Intelligence in Mllms
    ICCV 2025 ·

    Xinyu Fang

    DBLP profile ↗ORCID search ↗
14. Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction
    CVPR 2025 ·

    Rui Qian

    DBLP profile ↗ORCID search ↗
15. GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation
    NAACL 2025 ·

    Runchuan Zhu

    DBLP profile ↗ORCID search ↗
16. GenDoP: Auto-regressive Camera Trajectory Generation as a Director of Photography
    ICCV 2025 ·

    Mengchen Zhang

    DBLP profile ↗ORCID search ↗
17. Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity
    NeurIPS 2025 ·

    Yuhan Zhang

    DBLP profile ↗ORCID search ↗
18. HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance
    NeurIPS 2025 ·

    Jiazi Bu

    DBLP profile ↗ORCID search ↗
19. Hierachical Balance Packing: Towards Efficient Supervised Fine-tuning for Long-Context LLM
    NeurIPS 2025 ·

    Yongqiang Yao

    DBLP profile ↗ORCID search ↗
20. Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes
    CVPR 2025 ·

    Lihan Jiang

    DBLP profile ↗ORCID search ↗
21. IDArb: Intrinsic Decomposition for Arbitrary Number of Input Views and Illuminations
    ICLR 2025 ·

    Zhibing Li

    DBLP profile ↗ORCID search ↗
22. Imagine360: Immersive 360 Video Generation from Perspective Anchor
    NeurIPS 2025 ·

    Jing Tan

    DBLP profile ↗ORCID search ↗
23. InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model
    ACL 2025 ·

    Yuhang Zang

    DBLP profile ↗ORCID search ↗
24. Keyframe-Guided Creative Video Inpainting
    CVPR 2025 ·

    Yuwei Guo

    DBLP profile ↗ORCID search ↗
25. LEGION: Learning to Ground and Explain for Synthetic Image Detection
    ICCV 2025 ·

    Hengrui Kang

    DBLP profile ↗ORCID search ↗
26. LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models
    ICLR 2025 ·

    Junyan Ye

    DBLP profile ↗ORCID search ↗
27. Long Context Tuning for Video Generation
    ICCV 2025 ·

    Yuwei Guo

    DBLP profile ↗ORCID search ↗
28. MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models
    ICLR 2025 ·

    Ziyu Liu

    DBLP profile ↗ORCID search ↗
29. MM-IFEngine: Towards Multimodal Instruction Following
    ICCV 2025 ·

    Shengyuan Ding

    DBLP profile ↗ORCID search ↗
30. Mask-DPO: Generalizable Fine-grained Factuality Alignment of LLMs
    ICLR 2025 ·

    Yuzhe Gu

    DBLP profile ↗ORCID search ↗
31. Mixing Expert Knowledge: Bring Human Thoughts Back To the Game of Go
    NeurIPS 2025 ·

    Yichuan Ma

    DBLP profile ↗ORCID search ↗
32. More Data or Better Data? A Critical Analysis of Data Selection and Synthesis for Mathematical Reasoning
    EMNLP 2025 ·

    Yike Zhao

    DBLP profile ↗ORCID search ↗
33. Multi-Identity Human Image Animation with Structural Video Diffusion
    ICCV 2025 ·

    Zhenzhi Wang

    DBLP profile ↗ORCID search ↗
34. MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design
    ICML 2025 ·

    Haojie Duanmu

    DBLP profile ↗ORCID search ↗
35. OmniBal: Towards Fast Instruction-Tuning for Vision-Language Models via Omniverse Computation Balance
    ICML 2025 ·

    Yongqiang Yao

    DBLP profile ↗ORCID search ↗
36. OpenHuEval: Evaluating Large Language Model on Hungarian Specifics
    ACL 2025 ·

    Haote Yang

    DBLP profile ↗ORCID search ↗
37. Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulation
    ICLR 2025 ·

    Yang Tian

    DBLP profile ↗ORCID search ↗
38. Proc-GS: Procedural Building Generation for City Assembly with 3D Gaussians
    CVPR 2025 ·

    Yixuan Li

    DBLP profile ↗ORCID search ↗
39. ReSURE: Regularizing Supervision Unreliability for Multi-turn Dialogue Fine-tuning
    EMNLP 2025 ·

    Yiming Du

    DBLP profile ↗ORCID search ↗
40. SAM2LONG: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree
    ICCV 2025 ·

    Shuangrui Ding

    DBLP profile ↗ORCID search ↗
41. SampleAttention: Near-Lossless Acceleration of Long Context LLM Inference with Adaptive Structured Sparse Attention
    MLSys 2025 ·

    Qianchao Zhu

    DBLP profile ↗ORCID search ↗
42. Semi-off-Policy Reinforcement Learning for Vision-Language Slow-Thinking Reasoning
    NeurIPS 2025 ·

    Junhao Shen

    DBLP profile ↗ORCID search ↗
43. SongComposer: A Large Language Model for Lyric and Melody Generation in Song Composition
    ACL 2025 ·

    Shuangrui Ding

    DBLP profile ↗ORCID search ↗
44. SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation
    ICML 2025 ·

    Zihan Liu

    DBLP profile ↗ORCID search ↗
45. Training Language Models to Critique With Multi-agent Feedback
    EMNLP 2025 ·

    Tian Lan

    DBLP profile ↗ORCID search ↗
46. UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban Scenarios
    AAAI 2025 ·

    Baichuan Zhou

    DBLP profile ↗ORCID search ↗
47. Utilize the Flow Before Stepping into the Same River Twice: Certainty Represented Knowledge Flow for Refusal-Aware Instruction Tuning
    AAAI 2025 ·

    Runchuan Zhu

    DBLP profile ↗ORCID search ↗
48. VFLowOpt: A Token Pruning Framework for LMMs with Visual Information Flow-Guided Optimization
    ICCV 2025 ·

    Sihan Yang

    DBLP profile ↗ORCID search ↗
49. Video World Models with Long-term Spatial Memory
    NeurIPS 2025 ·

    Tong Wu

    DBLP profile ↗ORCID search ↗
50. VideoRoPE: What Makes for Good Video Rotary Position Embedding?
    ICML 2025 ·

    Xilin Wei

    DBLP profile ↗ORCID search ↗
51. Visual-RFT: Visual Reinforcement Fine-Tuning
    ICCV 2025 ·

    Ziyu Liu

    DBLP profile ↗ORCID search ↗
52. What are the Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets? Insights and Best Practices
    ACL 2025 ·

    Zhi Chen

    DBLP profile ↗ORCID search ↗
53. X-Prompt: Generalizable Auto-Regressive Visual Learning with In-Context Prompting
    ICCV 2025 ·

    Zeyi Sun

    DBLP profile ↗ORCID search ↗
54. daDPO: Distribution-Aware DPO for Distilling Conversational Abilities
    ACL 2025 ·

    Zhengze Zhang

    DBLP profile ↗ORCID search ↗
55. ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models
    NeurIPS 2024 ·

    Yuzhe Gu

    DBLP profile ↗ORCID search ↗
56. ANAH: Analytical Annotation of Hallucinations in Large Language Models
    ACL 2024 ·

    Ziwei Ji

    DBLP profile ↗ORCID search ↗
57. Ada-LEval: Evaluating long-context LLMs with length-adaptable benchmarks
    NAACL 2024 ·

    Chonghua Wang

    DBLP profile ↗ORCID search ↗
58. Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models
    ACL 2024 ·

    Zehui Chen

    DBLP profile ↗ORCID search ↗
59. AlchemistCoder: Harmonizing and Eliciting Code Capability by Hindsight Tuning on Multi-source Data
    NeurIPS 2024 ·

    Zifan Song

    DBLP profile ↗ORCID search ↗
60. Alpha-CLIP: A CLIP Model Focusing on Wherever you Want
    CVPR 2024 ·

    Zeyi Sun

    DBLP profile ↗ORCID search ↗
61. AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning
    ICLR 2024 ·

    Yuwei Guo

    DBLP profile ↗ORCID search ↗
62. Are We on the Right Way for Evaluating Large Vision-Language Models?
    NeurIPS 2024 ·

    Lin Chen

    DBLP profile ↗ORCID search ↗
63. Balanced Data Sampling for Language Model Training with Clustering
    ACL 2024 ·

    Yunfan Shao

    DBLP profile ↗ORCID search ↗
64. Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentation
    ECCV 2024 ·

    Shuangrui Ding

    DBLP profile ↗ORCID search ↗
65. BotChat: Evaluating LLMs' Capabilities of Having Multi-Turn Dialogues
    NAACL 2024 ·

    Haodong Duan

    DBLP profile ↗ORCID search ↗
66. Cinematic Behavior Transfer via NeRF-based Differentiable Filming
    CVPR 2024 ·

    Xuekun Jiang

    DBLP profile ↗ORCID search ↗
67. Code Needs Comments: Enhancing Code LLMs with Comment Augmentation
    ACL 2024 ·

    Demin Song

    DBLP profile ↗ORCID search ↗
68. CriticEval: Evaluating Large-scale Language Model as Critic
    NeurIPS 2024 ·

    Tian Lan

    DBLP profile ↗ORCID search ↗
69. EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI
    CVPR 2024 ·

    Tai Wang

    DBLP profile ↗ORCID search ↗
70. F-Eval: Asssessing Fundamental Abilities with Refined Evaluation Methods
    ACL 2024 ·

    Yu Sun

    DBLP profile ↗ORCID search ↗
71. FiVA: Fine-grained Visual Attribute Dataset for Text-to-Image Diffusion Models
    NeurIPS 2024 ·

    Tong Wu

    DBLP profile ↗ORCID search ↗
72. Flames: Benchmarking Value Alignment of LLMs in Chinese
    NAACL 2024 ·

    Kexin Huang

    DBLP profile ↗ORCID search ↗
73. From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models
    CVPR 2024 ·

    Rongjie Li

    DBLP profile ↗ORCID search ↗
74. GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation
    CVPR 2024 ·

    Tong Wu

    DBLP profile ↗ORCID search ↗
75. GPT4Point: A Unified Framework for Point-Language Understanding and Generation
    CVPR 2024 ·

    Zhangyang Qi

    DBLP profile ↗ORCID search ↗
76. GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image
    ECCV 2024 ·

    Xiao Fu

    DBLP profile ↗ORCID search ↗
77. HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting
    CVPR 2024 ·

    Xian Liu

    DBLP profile ↗ORCID search ↗
78. HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation
    NeurIPS 2024 ·

    Zhenzhi Wang

    DBLP profile ↗ORCID search ↗
79. HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion
    ICLR 2024 ·

    Xian Liu

    DBLP profile ↗ORCID search ↗
80. Identifying Semantic Induction Heads to Understand In-Context Learning
    ACL 2024 ·

    Jie Ren

    DBLP profile ↗ORCID search ↗
81. InterControl: Zero-shot Human Interaction Generation by Controlling Every Joint
    NeurIPS 2024 ·

    Zhenzhi Wang

    DBLP profile ↗ORCID search ↗
82. InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD
    NeurIPS 2024 ·

    Xiaoyi Dong

    DBLP profile ↗ORCID search ↗
83. Lean Workbook: A large-scale Lean problem set formalized from natural language math problems
    NeurIPS 2024 ·

    Huaiyuan Ying

    DBLP profile ↗ORCID search ↗
84. Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback
    ICML 2024 ·

    Songyang Gao

    DBLP profile ↗ORCID search ↗
85. LongWanjuan: Towards Systematic Measurement for Long Text Quality
    EMNLP 2024 ·

    Xiaoran Liu

    DBLP profile ↗ORCID search ↗
86. MGF: Mixed Gaussian Flow for Diverse Trajectory Prediction
    NeurIPS 2024 ·

    Jiahe Chen

    DBLP profile ↗ORCID search ↗
87. MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding
    NeurIPS 2024 ·

    Xinyu Fang

    DBLP profile ↗ORCID search ↗
88. MMBench: Is Your Multi-modal Model an All-Around Player?
    ECCV 2024 ·

    Yuan Liu

    DBLP profile ↗ORCID search ↗
89. MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs
    NeurIPS 2024 ·

    Ziyu Liu

    DBLP profile ↗ORCID search ↗
90. MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations
    NeurIPS 2024 ·

    Ruiyuan Lyu

    DBLP profile ↗ORCID search ↗
91. Make-it-Real: Unleashing Large Multimodal Model for Painting 3D Objects with Realistic Materials
    NeurIPS 2024 ·

    Ye Fang

    DBLP profile ↗ORCID search ↗
92. MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark
    ACL 2024 ·

    Hongwei Liu

    DBLP profile ↗ORCID search ↗
93. MuxServe: Flexible Spatial-Temporal Multiplexing for Multiple LLM Serving
    ICML 2024 ·

    Jiangfei Duan

    DBLP profile ↗ORCID search ↗
94. Navigating the OverKill in Large Language Models
    ACL 2024 ·

    Chenyu Shi

    DBLP profile ↗ORCID search ↗
95. OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation
    CVPR 2024 ·

    Qidong Huang

    DBLP profile ↗ORCID search ↗
96. OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI
    NeurIPS 2024 ·

    Zhen Huang

    DBLP profile ↗ORCID search ↗
97. Omni6D: Large-Vocabulary 3D Object Dataset for Category-Level 6D Object Pose Estimation
    ECCV 2024 ·

    Mengchen Zhang

    DBLP profile ↗ORCID search ↗
98. OneLLM: One Framework to Align All Modalities with Language
    CVPR 2024 ·

    Jiaming Han

    DBLP profile ↗ORCID search ↗
99. PointLLM: Empowering Large Language Models to Understand Point Clouds
    ECCV 2024 ·

    Runsen Xu

    DBLP profile ↗ORCID search ↗
100. Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs
     NeurIPS 2024 ·

     Yuxuan Qiao

     DBLP profile ↗ORCID search ↗
101. ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs
     EMNLP 2024 ·

     Jingming Zhuo

     DBLP profile ↗ORCID search ↗
102. Rethinking Image-to-Video Adaptation: An Object-Centric Perspective
     ECCV 2024 ·

     Rui Qian

     DBLP profile ↗ORCID search ↗
103. SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models
     ACL 2024 ·

     Lijun Li

     DBLP profile ↗ORCID search ↗
104. SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction
     ICLR 2024 ·

     Xinyuan Chen

     DBLP profile ↗ORCID search ↗
105. Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering
     CVPR 2024 ·

     Tao Lu

     DBLP profile ↗ORCID search ↗
106. Scaling Behavior for Large Language Models regarding Numeral Systems: An Example using Pythia
     EMNLP 2024 ·

     Zhejian Zhou

     DBLP profile ↗ORCID search ↗
107. Scaling Laws of RoPE-based Extrapolation
     ICLR 2024 ·

     Xiaoran Liu

     DBLP profile ↗ORCID search ↗
108. ShareGPT4V: Improving Large Multi-modal Models with Better Captions
     ECCV 2024 ·

     Lin Chen

     DBLP profile ↗ORCID search ↗
109. ShareGPT4Video: Improving Video Understanding and Generation with Better Captions
     NeurIPS 2024 ·

     Lin Chen

     DBLP profile ↗ORCID search ↗
110. SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models
     ECCV 2024 ·

     Yuwei Guo

     DBLP profile ↗ORCID search ↗
111. Streaming Long Video Understanding with Large Language Models
     NeurIPS 2024 ·

     Rui Qian

     DBLP profile ↗ORCID search ↗
112. T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step
     ACL 2024 ·

     Zehui Chen

     DBLP profile ↗ORCID search ↗
113. Towards Text-guided 3D Scene Composition
     CVPR 2024 ·

     Qihang Zhang

     DBLP profile ↗ORCID search ↗
114. Turn Waste into Worth: Rectifying Top-k Router of MoE
     EMNLP 2024 ·

     Zhiyuan Zeng

     DBLP profile ↗ORCID search ↗
115. Uncertainty Aware Learning for Language Model Alignment
     ACL 2024 ·

     Yikun Wang

     DBLP profile ↗ORCID search ↗
116. Unified Human-Scene Interaction via Prompted Chain-of-Contacts
     ICLR 2024 ·

     Zeqi Xiao

     DBLP profile ↗ORCID search ↗
117. VBench: Comprehensive Benchmark Suite for Video Generative Models
     CVPR 2024 ·

     Ziqi Huang

     DBLP profile ↗ORCID search ↗
118. VLMEvalKit: An Open-Source ToolKit for Evaluating Large Multi-Modality Models
     ACM MM 2024 ·

     Haodong Duan

     DBLP profile ↗ORCID search ↗
119. VideoBooth: Diffusion-based Video Generation with Image Prompts
     CVPR 2024 ·

     Yuming Jiang

     DBLP profile ↗ORCID search ↗
120. X-neuron: Interpreting, Locating and Editing of Neurons in Reinforcement Learning Policy
     IROS 2024 ·

     Yuhong Ge

     DBLP profile ↗ORCID search ↗