publications

2026

1. CVPR

   VQ-VA World: Towards High-Quality Visual Question-Visual Answering

   Chenhui Gou^*, Zilong Chen^*, Zeyu Wang^*, and 10 more authors

   In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). , 2026

   Bib

   @inproceedings{gou2026vqva,
     title = {VQ-VA World: Towards High-Quality Visual Question-Visual Answering},
     author = {Gou, Chenhui and Chen, Zilong and Wang, Zeyu and Li, Feng and Zhu, Deyao and Duan, Zicheng and Li, Kunchang and Deng, Chaorui and Yuan, Hongyi and Fan, Haoqi and Xie, Cihang and Cai, Jianfei and Rezatofighi, Hamid},
     year = {2026},
     booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
   }

2. CVPR

   An Empirical Study on How Video-LLMs Answer Video Questions

   Chenhui Gou, Ziyu Ma, Zicheng Duan, and 6 more authors

   In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

   Bib

   @inproceedings{gou2026empirical,
     title = {An Empirical Study on How Video-LLMs Answer Video Questions},
     author = {Gou, Chenhui and Ma, Ziyu and Duan, Zicheng and He, Haoyu and Chen, Feng and Liu, Akide and Zhuang, Bohan and Cai, Jianfei and Rezatofighi, Hamid},
     year = {2026},
     booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
   }

3. AAAI

   Where and What Matters: Sensitivity-Aware Task Vectors for Many-Shot Multimodal In-Context Learning

   Ziyu Ma^*, Chenhui Gou^*, Yiming Hu, and 4 more authors

   In AAAI Conference on Artificial Intelligence (AAAI), 2026

   Bib

   @inproceedings{ma2026sensitivity,
     title = {Where and What Matters: Sensitivity-Aware Task Vectors for Many-Shot Multimodal In-Context Learning},
     author = {Ma, Ziyu and Gou, Chenhui and Hu, Yiming and Wang, Yong and Chu, Xiangxiang and Zhuang, Bohan and Cai, Jianfei},
     year = {2026},
     booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
   }

4. ICLR

   Sparsity Forcing: Reinforcing Token Sparsity of MLLMs

   Feng Chen, Yefei He, Lequan Lin, and 4 more authors

   In International Conference on Learning Representations (ICLR), 2026

   Bib

   @inproceedings{chen2026sparsity,
     title = {Sparsity Forcing: Reinforcing Token Sparsity of MLLMs},
     author = {Chen, Feng and He, Yefei and Lin, Lequan and Gou, Chenhui and Liu, Jing and Zhuang, Bohan and Wu, Qi},
     year = {2026},
     booktitle = {International Conference on Learning Representations (ICLR)},
   }

5. CVPR

   Evaluating and Advancing Multimodal Large Language Models in Ability Lens

   Feng Chen^*, Chenhui Gou, Jing Liu, and 6 more authors

   In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Findings, 2026

   Bib

   @inproceedings{chen2026evaluating,
     title = {Evaluating and Advancing Multimodal Large Language Models in Ability Lens},
     author = {Chen, Feng and Gou, Chenhui and Liu, Jing and Yang, Yang and Li, Zhaoyang and Zhang, Jiyuan and Sun, Zhenbang and Zhuang, Bohan and Wu, Qi},
     year = {2026},
     booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Findings},
   }

2025

1. Tech Report

   Seed1.5-VL Technical Report

   ByteDance Seed Team

   Contributor. , 2025

   Bib

   @article{seed15vl2025,
     title = {Seed1.5-VL Technical Report},
     author = {Team, ByteDance Seed},
     year = {2025},
   }

2. BAGEL

   Emerging Properties in Unified Multimodal Pretraining

   ByteDance BAGEL Team

   Core contributor. , May 2025

   Bib Code

   @article{bagel2025,
     title = {Emerging Properties in Unified Multimodal Pretraining},
     author = {Team, ByteDance BAGEL},
     month = may,
     year = {2025},
   }

3. Preprint

   LightBagel: A Light-Weighted, Double Fusion Framework for Unified Multimodal Understanding and Generation

   Zeyu Wang^*, Zilong Chen^*, Chenhui Gou^*, and 8 more authors

   2025

   Bib

   @article{wang2025lightbagel,
     title = {LightBagel: A Light-Weighted, Double Fusion Framework for Unified Multimodal Understanding and Generation},
     author = {Wang, Zeyu and Chen, Zilong and Gou, Chenhui and Li, Feng and Deng, Chaorui and Zhu, Deyao and Li, Kunchang and Yu, Weihao and Tu, Haoqin and Xie, Cihang and Fan, Haoqi},
     year = {2025},
   }

4. Preprint

   UniMedVL: Unifying Medical Multimodal Understanding and Generation Through Observation-Knowledge-Analysis

   . Contributor. , 2025

   Bib

   @article{unimedvl2025,
     title = {UniMedVL: Unifying Medical Multimodal Understanding and Generation Through Observation-Knowledge-Analysis},
     author = {},
     year = {2025},
   }

5. CVPR

   DrVideo: Document Retrieval Based Long Video Understanding

   Ziyu Ma^*, Chenhui Gou^*, Hengcan Shi, and 4 more authors

   In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

   Bib

   @inproceedings{ma2025drvideo,
     title = {DrVideo: Document Retrieval Based Long Video Understanding},
     author = {Ma, Ziyu and Gou, Chenhui and Shi, Hengcan and Sun, Bin and Li, Shutao and Rezatofighi, Hamid and Cai, Jianfei},
     year = {2025},
     booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
   }

6. EMNLP

   InfiniBench: A Comprehensive Benchmark for Large Multimodal Models in Very Long Video Understanding

   Kirolos Ataallah, Chenhui Gou, Eslam Mohamed Bakr, and 3 more authors

   In Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025

   Bib

   @inproceedings{ataallah2025infinibench,
     title = {InfiniBench: A Comprehensive Benchmark for Large Multimodal Models in Very Long Video Understanding},
     author = {Ataallah, Kirolos and Gou, Chenhui and Bakr, Eslam Mohamed and Pahwa, Khushbu and Ding, Jian and Elhoseiny, Mohamed},
     year = {2025},
     booktitle = {Conference on Empirical Methods in Natural Language Processing (EMNLP)},
   }

7. Preprint

   LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models

   Zicheng Duan, Jiatong Xia, Zeyu Zhang, and 7 more authors

   2025

   Bib

   @article{duan2025liveworld,
     title = {LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models},
     author = {Duan, Zicheng and Xia, Jiatong and Zhang, Zeyu and Zhang, Wenbo and Zhou, Gengze and Gou, Chenhui and He, Yefei and Chen, Feng and Zhang, Xinyu and Liu, Lingqiao},
     year = {2025},
   }

8. CVPR

   Point-Cache: Test-time Dynamic and Hierarchical Cache for Robust and Generalizable Point Cloud Analysis

   Hongyu Sun, Qiuhong Ke, Ming Cheng, and 4 more authors

   In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

   Bib

   @inproceedings{sun2025pointcache,
     title = {Point-Cache: Test-time Dynamic and Hierarchical Cache for Robust and Generalizable Point Cloud Analysis},
     author = {Sun, Hongyu and Ke, Qiuhong and Cheng, Ming and Wang, Yongcai and Li, Deying and Gou, Chenhui and Cai, Jianfei},
     year = {2025},
     booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
   }

2024

1. Preprint

   Mobile-VideoGPT: Fast and Accurate Video Understanding Language Model

   Abdelrahman Shaker, Muhammad Maaz, Chenhui Gou, and 3 more authors

   2024

   Bib

   @article{shaker2024mobilevideogpt,
     title = {Mobile-VideoGPT: Fast and Accurate Video Understanding Language Model},
     author = {Shaker, Abdelrahman and Maaz, Muhammad and Gou, Chenhui and Rezatofighi, Hamid and Khan, Salman and Khan, Fahad Shahbaz},
     year = {2024},
   }

2. Preprint

   How Well Can Vision Language Models See Image Details?

   Chenhui Gou, Faizan Khan, Deyao Zhu, and 4 more authors

   2024

   Bib

   @article{gou2024howwell,
     title = {How Well Can Vision Language Models See Image Details?},
     author = {Gou, Chenhui and Khan, Faizan and Zhu, Deyao and Felemban, Abdulwahab and Cai, Jianfei and Rezatofighi, Hamid and Elhoseiny, Mohamed},
     year = {2024},
   }

3. CVPR

   JRDB-PanoTrack: An Open-World Panoptic Segmentation and Tracking Robotic Dataset in Crowded Human Environments

   Duy-Tho Le^*, Chenhui Gou^*, Stavya Datta, and 4 more authors

   In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

   Bib

   @inproceedings{le2024jrdb,
     title = {JRDB-PanoTrack: An Open-World Panoptic Segmentation and Tracking Robotic Dataset in Crowded Human Environments},
     author = {Le, Duy-Tho and Gou, Chenhui and Datta, Stavya and Shi, Hengcan and Reid, Ian and Cai, Jianfei and Rezatofighi, Hamid},
     year = {2024},
     booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
   }

2023

1. Preprint

   Strong and Controllable Blind Image Decomposition

   Zeyu Zhang^*, Junlin Han^*, Chenhui Gou^*, and 2 more authors

   2023

   Bib

   @article{zhang2023blind,
     title = {Strong and Controllable Blind Image Decomposition},
     author = {Zhang, Zeyu and Han, Junlin and Gou, Chenhui and Li, Hongdong and Zheng, Liang},
     year = {2023},
   }

2022

1. NeurIPS

   RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer

   Jian Wang^*, Chenhui Gou^*, Qiman Wu^*, and 4 more authors

   In Advances in Neural Information Processing Systems (NeurIPS). Spotlight Presentation , 2022

   Bib

   @inproceedings{wang2022rtformer,
     title = {RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer},
     author = {Wang, Jian and Gou, Chenhui and Wu, Qiman and Feng, Haocheng and Han, Junyu and Ding, Errui and Wang, Jingdong},
     year = {2022},
     booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
   }