HD
Haodong Duan
cs.CVcs.AIcs.CLcs.LGcs.MMeess.IVcs.IR
On Valency
published · living versionsW_bcr6ukuw·v1 · currentpublished
PixelBench: Can LLMs Understand and Generate Images Pixel by Pixel?
with Haoquan Zhang, Feiyang Liu, Juanxi Tian, Wanhua Li +1
1 version
Preprints & journals
62 papers in the corpus · 2017–2026V-ICAL Bench: Evaluating Video In-Context Learning for Multimodal Agents in Interactive Environments2609.15683v2 · Ziqian Fan, Shibo Xu, Junjie Li et al.2026 · 0 citationsarXiv
FARS: A Fully Automated Research System Deployed at Scale2606.31651v2 · Qiong Tang, Tianxiang Sun, Xiangkun Hu et al.2026 · 0 citationsarXiv
Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games2606.19338v1 · Shengyuan Ding, Xilin Wei, Xinyu Fang et al.2026 · 0 citationsarXiv
Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields2606.11042v4 · Liya Zhu, Jingzhe Ding, Jian Zhang et al.2026 · 0 citationsarXiv
Can Retrieval Heads See Images? Multimodal Retrieval Heads in Long-Context Vision-Language Models2605.27243v3 · Aaron Branson Cigres Li, Zhaowei Wang, Yu Zhao et al.2026 · 0 citationsarXiv
OpenCompass: A Universal Evaluation Platform for Large Language Models2605.19276v3 · Maosong Cao, Kai Chen, Haodong Duan et al.2026 · 0 citationsarXiv
Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context2605.13831v2 · Zhaowei Wang, Lishu Luo, Haodong Duan et al.2026 · 0 citationsarXiv
WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation2605.10912v1 · Shuangrui Ding, Xuanlang Dai, Long Xing et al.2026 · 0 citationsarXiv
OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces2605.08904v1 · Xiaozhe Li, Jixuan Chen, Xinyu Fang et al.2026 · 0 citationsarXiv
Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs2605.08905v1 · Xiaozhe Li, Xinyu Fang, Shengyuan Ding et al.2026 · 0 citationsarXiv
Project Imaging-X: A Survey of 1000+ Open-Access Medical Imaging Datasets for Foundation Model Development2603.27460v1 · Zhongying Deng, Cheng Tang, Ziyan Huang et al.2026 · 0 citationsarXiv
PosterIQ: A Design Perspective Benchmark for Poster Understanding and Generation2603.24078v1 · Yuheng Feng, Wen Zhang, Haodong Duan et al.2026 · 0 citationsarXiv
MIBench: Evaluating LMMs on Multimodal Interaction2603.13427v1 · Yu Miao, Zequn Yang, Yake Wei et al.2026 · 0 citationsarXiv
RISE-Video: Can Video Generators Decode Implicit World Rules?2602.05986v1 · Mingxin Liu, Shuran Ma, Shibei Meng et al.2026 · 0 citationsarXiv
SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligence2512.22334v3 · Yiheng Wang, Yixin Chen, Shuo Li et al.2025 · 0 citationsarXiv
ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning2512.05111v1 · Shengyuan Ding, Xinyu Fang, Ziyu Liu et al.2025 · 0 citationsarXiv
Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning2510.27606v2 · Yuhong Liu, Beichen Zhang, Yuhang Zang et al.2025 · 0 citationsarXiv
NP-Engine: Empowering Optimization Reasoning in Large Language Models with Verifiable Synthetic NP Problems2510.16476v1 · Xiaozhe Li, Xinyu Fang, Shengyuan Ding et al.2025 · 0 citationsarXiv
SPARK: Synergistic Policy And Reward Co-Evolving Framework2509.22624v1 · Ziyu Liu, Yuhang Zang, Shengyuan Ding et al.2025 · 0 citationsarXiv
A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers2508.21148v2 · Ming Hu, Chenglong Ma, Wei Li et al.2025 · 1 citationarXiv
Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings2506.04997v1 · Yubo Ma, Jinsong Li, Yuhang Zang et al.2025 · 5 citationsarXiv
GOBench: Benchmarking Geometric Optics Generation and Understanding of MLLMs2506.00991v2 · Xiaorong Zhu, Ziheng Jia, Jiarui Wang et al.2025 · 3 citationsarXiv
MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence2505.23764v3 · Sihan Yang, Runsen Xu, Yiman Xie et al.2025 · 0 citationsarXiv
MM-IFEngine: Towards Multimodal Instruction Following2504.07957v2 · Shengyuan Ding, Shenxi Wu, Xiangyu Zhao et al.2025 · 3 citationsarXiv
LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?2503.19990v4 · Kexian Tang, Junyao Gao, Yanhong Zeng et al.2025 · 2 citationsarXiv
Image Quality Assessment: From Human to Machine Preference2503.10078v1 · Chunyi Li, Yuan Tian, Xiaoyue Ling et al.2025 · 12 citationsarXiv
Information Density Principle for MLLM Benchmarks2503.10079v1 · Chunyi Li, Xiaozhe Li, Zicheng Zhang et al.2025 · 1 citationarXiv
VisualPRM: An Effective Process Reward Model for Multimodal Reasoning2503.10291v1 · Weiyun Wang, Zhangwei Gao, Lianjie Chen et al.2025 · 0 citationsarXiv
OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference2502.18411v2 · Xiangyu Zhao, Shengyuan Ding, Zicheng Zhang et al.2025 · 5 citationsarXiv
VideoRoPE: What Makes for Good Video Rotary Position Embedding?2502.05173v3 · Xilin Wei, Xiaoran Liu, Yuhang Zang et al.2025 · 0 citationsarXiv
InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model2501.12368v2 · Yuhang Zang, Xiaoyi Dong, Pan Zhang et al.2025 · 9 citationsarXiv
Redundancy Principles for MLLMs Benchmarks2501.13953v2 · Zicheng Zhang, Xiangyu Zhao, Xinyu Fang et al.2025 · 4 citationsarXiv
OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?2501.05510v2 · Yifei Li, Junbo Niu, Ziyang Miao et al.2025 · 21 citationsarXiv
BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning2501.03226v3 · Beichen Zhang, Yuhong Liu, Xiaoyi Dong et al.2025 · 0 citationsarXiv
InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions2412.09596v1 · Pan Zhang, Xiaoyi Dong, Yuhang Cao et al.2024 · 1 citationarXiv
MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs2411.15296v2 · Chaoyou Fu, Yi-Fan Zhang, Shukang Yin et al.2024 · 4 citationsarXiv
MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models2410.17637v1 · Ziyu Liu, Yuhang Zang, Xiaoyi Dong et al.2024 · 0 citationsarXiv
GMAI-MMBench: A Comprehensive Multimodal Evaluation Benchmark Towards General Medical AI2408.03361v7 · Pengcheng Chen, Jin Ye, Guoan Wang et al.2024 · 25 citationsarXiv
VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models2407.11691v5 · Haodong Duan, Xinyu Fang, Junming Yang et al.2024 · 95 citationsarXiv
InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output2407.03320v1 · Pan Zhang, Xiaoyi Dong, Yuhang Zang et al.2024 · 3 citationsarXiv
MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuning2406.17770v2 · Xiangyu Zhao, Xiangtai Li, Haodong Duan et al.2024 · 1 citationarXiv
MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding2406.14515v3 · Xinyu Fang, Kangrui Mao, Haodong Duan et al.2024 · 15 citationsarXiv
ShareGPT4Video: Improving Video Understanding and Generation with Better Captions2406.04325v1 · Lin Chen, Xilin Wei, Jinsong Li et al.2024 · 69 citationsarXiv
MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark2405.12209v1 · Hongwei Liu, Zilong Zheng, Yuxuan Qiao et al.2024 · 17 citationsarXiv
InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD2404.06512v1 · Xiaoyi Dong, Pan Zhang, Yuhang Zang et al.2024 · 16 citationsarXiv
Are We on the Right Way for Evaluating Large Vision-Language Models?2403.20330v2 · Lin Chen, Jinsong Li, Xiaoyi Dong et al.2024 · 106 citationsarXiv
InternLM2 Technical Report2403.17297v1 · Zheng Cai, Maosong Cao, Haojiong Chen et al.2024 · 29 citationsarXiv
InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model2401.16420v1 · Xiaoyi Dong, Pan Zhang, Yuhang Zang et al.2024 · 12 citationsarXiv
InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition2309.15112v5 · Pan Zhang, Xiaoyi Dong, Bin Wang et al.2023 · 40 citationsarXiv
SkeleTR: Towrads Skeleton-based Action Recognition in the Wild2309.11445v1 · Haodong Duan, Mingze Xu, Bing Shuai et al.2023 · 0 citationsarXiv
Career total: 68 works. 62 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.