|
Wei Chen
PhD Student
Department of Computer Science and Engineering
The Hong Kong University of Science and Technology
Email: csewei.chen AT connect DOT ust DOT hk
|
|
Biography
I am a PhD student in the Department of Computer Science and Engineering at The Hong Kong University of Science and Technology, where I am advised by Prof. Long Chen in the LONG Group.
Prior to this, I obtained my bachelor's degree from the School of Computer Science at Wuhan University, under the supervision of Prof. Yu Wu.
Research Interests
My research interests lie in multimodal agents, which include:
-
Scalable task and environment synthesis for long-horizon multimodal agents
-
Efficient and effective multimodal agentic memory
-
Scalable agentic reinforcement learning for multimodal agents
Selected Publications
Sprout: Building Dynamic Memory While Reasoning for Agentic Video Understanding
Wei Chen, Xuanyu Zheng, Yancheng Long, Haoyang Xu, Kaiyu Jiang, Bin Wen, Tingting Gao, Han Li, Long Chen
Relation-R1: Cognitive Chain-of-Thought Guided Reinforcement Learning for Unified Relational Comprehension
Lin Li*, Wei Chen*, Jiahui Li, Kwang-Ting Cheng, Long Chen
AAAI Conference on Artificial Intelligence (
AAAI), 2026
[paper]
[code]
Thyme: Think Beyond Images
Yi-Fan Zhang, Xingyu Lu, Shukang Yin, Chaoyou Fu, Wei Chen, Xiao Hu, Bin Wen, et al.
International Conference on Learning Representations (
ICLR), 2026
[paper]
[code]
Decoupling Contrastive Decoding: Robust Hallucination Mitigation in Multimodal Large Language Models
Wei Chen, Xin Yan, Bin Wen, Fan Yang, Tingting Gao, Di Zhang, Long Chen
Neural Information Processing Systems (
NeurIPS), 2025
[paper]
[code]
CoMM: A Coherent Interleaved Image-Text Dataset for Multimodal Understanding and Generation
Wei Chen*, Lin Li*, Yongqi Yang*, Bin Wen, Fan Yang, Tingting Gao, Yu Wu, Long Chen
Computer Vision and Pattern Recognition (
CVPR Highlight), 2025
[paper]
[code]
An Efficient and Effective Transformer Decoder-Based
Framework for Multi-Task Visual Grounding
Wei Chen, Long Chen, Yu Wu
European Conference on Computer Vision (
ECCV), 2024
[paper]
[code]