I am a third-year M.S. student at the School of Artificial Intelligence, Beijing University of Posts and Telecommunications (BUPT), under the supervision of Chun-Guang Li. I plan to pursue a Ph.D. after completing my master's degree.
My current research interests are efficient attention and recursive self-improvement. Previously, I worked on white-box models. Feel free to reach out for discussions or collaboration!
Warning
Problem: The current name of your GitHub Pages repository ("Solution: Please consider renaming the repository to "
http://".
However, if the current repository name is intended, you can ignore this message by removing "{% include widgets/debug_repo_name.html %}" in index.html.
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "Education
-
Beijing University of Posts and TelecommunicationsSchool of Artificial Intelligence
M.S. StudentSep. 2024 - present -
Beijing University of Posts and TelecommunicationsSchool of Artificial Intelligence
B.S. in Artificial IntelligenceSep. 2020 - Jun. 2024
Experience
-
Alibaba GroupDreamX Team, AmapResearch InternApr. 2026 - Jul. 2026
Honors & Awards
-
Top Reviewer, NeurIPS2026
-
National Scholarships, Ministry of Education, China2025
-
First Class Award Scholarship, BUPT2025
-
First Class Award Scholarship, BUPT2024
-
Kaggle Competition Bronze Medal2023
News
Selected Publications (view all )
vSFT: Learning to Verbally Tune Agents at Test Time
Qishuai Wen, Rui Chen, Haiwen Li, Zhiyuan Huang, Qiwen Gu, Bingjie Gao, Geng Li, Jing Tang, Chu Xiangxiang, Chun-Guang Li
Under review
We propose vSFT, a test-time adaptation method for agents that provides a learnable, effective self-improvement mechanism by iteratively internalizing verbal feedback in a closed loop.
vSFT: Learning to Verbally Tune Agents at Test Time
Qishuai Wen, Rui Chen, Haiwen Li, Zhiyuan Huang, Qiwen Gu, Bingjie Gao, Geng Li, Jing Tang, Chu Xiangxiang, Chun-Guang Li
Under review
We propose vSFT, a test-time adaptation method for agents that provides a learnable, effective self-improvement mechanism by iteratively internalizing verbal feedback in a closed loop.
Mixture-of-Top-k Attention: Efficient Attention via Scalable Fast Weights
Qishuai Wen, Zhiyuan Huang, Xianghan Meng, Wei He, Chun-Guang Li
NeurIPS 2026
We introduce a fast-weight perspective that unifies existing efficient attention designs, thereby revealing the limitations of prior methods and addressing them with our proposed Mixture-of-Top-k Attention (MiTA).
Mixture-of-Top-k Attention: Efficient Attention via Scalable Fast Weights
Qishuai Wen, Zhiyuan Huang, Xianghan Meng, Wei He, Chun-Guang Li
NeurIPS 2026
We introduce a fast-weight perspective that unifies existing efficient attention designs, thereby revealing the limitations of prior methods and addressing them with our proposed Mixture-of-Top-k Attention (MiTA).
Towards Interpretable and Efficient Attention: Compressing All by Contracting a Few
Qishuai Wen, Zhiyuan Huang, Chun-Guang Li
NeurIPS 2025 Spotlight
We propose an interpretable and efficient attention mechanism, Contract-and-Broadcast Self-Attention (CBSA), which also unifies a wide range of existing methods, including channel attention, linear attention, and full attention.
Towards Interpretable and Efficient Attention: Compressing All by Contracting a Few
Qishuai Wen, Zhiyuan Huang, Chun-Guang Li
NeurIPS 2025 Spotlight
We propose an interpretable and efficient attention mechanism, Contract-and-Broadcast Self-Attention (CBSA), which also unifies a wide range of existing methods, including channel attention, linear attention, and full attention.
Rethinking Decoders for Transformer-based Semantic Segmentation: A Compression Perspective
Qishuai Wen, Chun-Guang Li
NeurIPS 2024
We establish connections between compression and semantic segmentation, particularly between principal component analysis and Transformer decoders. Based on this perspective, we derive DEPICT, a white-box, fully attentional decoder that is lightweight, interpretable, and robust.
Rethinking Decoders for Transformer-based Semantic Segmentation: A Compression Perspective
Qishuai Wen, Chun-Guang Li
NeurIPS 2024
We establish connections between compression and semantic segmentation, particularly between principal component analysis and Transformer decoders. Based on this perspective, we derive DEPICT, a white-box, fully attentional decoder that is lightweight, interpretable, and robust.