Publications

2025

1. arXiv’25/05

   HoliTom: Holistic Token Merging for Fast Video Large Language Models

   Kele Shao, Keda Tao, Can Qin, Haoxuan You, Yang Sui, and Huan Wang^†

   arXiv preprint arXiv:2505.21334, 2025

   arXiv Bib Code Website

   @article{shao2025holitom,
     title = {HoliTom: Holistic Token Merging for Fast Video Large Language Models},
     author = {Shao, Kele and Tao, Keda and Qin, Can and You, Haoxuan and Sui, Yang and Wang, Huan},
     journal = {arXiv preprint arXiv:2505.21334},
     year = {2025},
   }

2. arXiv’25/05

   Can MLLMs Guide Me Home? A Benchmark Study on Fine-Grained Visual Reasoning from Transit Maps

   Sicheng Feng^* , Song Wang^*, Shuyi Ouyang, Lingdong Kong, Zikai Song, Jianke Zhu, Huan Wang^† , and Xinchao Wang

   arXiv preprint arXiv:2505.18675, 2025

   Abs arXiv Bib Code Website Dataset 量子位

   Multimodal large language models (MLLMs) have recently achieved significant progress in visual tasks, including semantic scene understanding and text-image alignment, with reasoning variants enhancing performance on complex tasks involving mathematics and logic. However, their capacity for reasoning tasks involving fine-grained visual understanding remains insufficiently evaluated. To address this gap, we introduce ReasonMap, a benchmark designed to assess the fine-grained visual understanding and spatial reasoning abilities of MLLMs. ReasonMap encompasses high-resolution transit maps from 30 cities across 13 countries and includes 1,008 question-answer pairs spanning two question types and three templates. Furthermore, we design a two-level evaluation pipeline that properly assesses answer correctness and quality. Comprehensive evaluations of 15 popular MLLMs, including both base and reasoning variants, reveal a counterintuitive pattern: among open-source models, base models outperform reasoning ones, while the opposite trend is observed in closed-source models. Additionally, performance generally degrades when visual inputs are masked, indicating that while MLLMs can leverage prior knowledge to answer some questions, fine-grained visual reasoning tasks still require genuine visual perception for strong performance. Our benchmark study offers new insights into visual reasoning and contributes to investigating the gap between open-source and closed-source models.

   @article{feng2025canmllms,
     title = {Can MLLMs Guide Me Home? A Benchmark Study on Fine-Grained Visual Reasoning from Transit Maps},
     author = {Feng, Sicheng and Wang, Song and Ouyang, Shuyi and Kong, Lingdong and Song, Zikai and Zhu, Jianke and Wang, Huan and Wang, Xinchao},
     journal = {arXiv preprint arXiv:2505.18675},
     year = {2025},
     dataset = {https://huggingface.co/datasets/FSCCS/ReasonMap},
     qbitai = {https://mp.weixin.qq.com/s/sPJLQtHgl5DZghWLWa_H3Q},
   }

3. CVPR’25

   DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models

   Keda Tao, Can Qin, Haoxuan You, Yang Sui, and Huan Wang

   CVPR, 2025

   arXiv Bib Code

   @inproceedings{tao2025dycoke,
     title = {DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models},
     author = {Tao, Keda and Qin, Can and You, Haoxuan and Sui, Yang and Wang, Huan},
     booktitle = {CVPR},
     year = {2025},
   }

4. ICLR’25

   Accessing Vision Foundation Models at ImageNet-level Costs

   Yitian Zhang, Xu Ma, Yue Bai, Huan Wang, and Yun Fu

   ICLR, 2025

   arXiv Bib Code

   @inproceedings{zhang2024accessing,
     title = {Accessing Vision Foundation Models at ImageNet-level Costs},
     author = {Zhang, Yitian and Ma, Xu and Bai, Yue and Wang, Huan and Fu, Yun},
     booktitle = {ICLR},
     year = {2025},
   }

2024

1. arXiv’24/11

   Is Oracle Pruning the True Oracle?

   Sicheng Feng, Keda Tao, and Huan Wang

   arXiv preprint arXiv:2412.00143, 2024

   arXiv Bib Code Website

   @article{feng2024oracle,
     title = {Is Oracle Pruning the True Oracle?},
     author = {Feng, Sicheng and Tao, Keda and Wang, Huan},
     journal = {arXiv preprint arXiv:2412.00143},
     year = {2024},
   }

2. ACM MM’24

   Towards Real-time Video Compressive Sensing on Mobile Devices

   Miao Cao , Lishun Wang, Huan Wang , Guoqing Wang, and Xin Yuan

   ACM MM, 2024

   arXiv Bib Code

   @inproceedings{cao2024towards,
     title = {Towards Real-time Video Compressive Sensing on Mobile Devices},
     author = {Cao, Miao and Wang, Lishun and Wang, Huan and Wang, Guoqing and Yuan, Xin},
     booktitle = {ACM MM},
     year = {2024},
   }

3. ECCV’24 Oral

   A Simple Low-bit Quantization Framework for Video Snapshot Compressive Imaging

   Miao Cao , Lishun Wang, Huan Wang, and Xin Yuan

   ECCV, 2024

   arXiv Bib Code

   @inproceedings{cao2024simple,
     title = {A Simple Low-bit Quantization Framework for Video Snapshot Compressive Imaging},
     author = {Cao, Miao and Wang, Lishun and Wang, Huan and Yuan, Xin},
     booktitle = {ECCV},
     year = {2024},
   }