logo
today local_bar

Kan Li

Full Professor, Beijing Institute of Technology

4 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 1

1 paper
Wednesday, December 3, 2025 · 11:00 AM → 2:00 PM
Exhibit Hall C,D,E
Silencer: From Discovery to Mitigation of Self-Bias in LLM-as-Benchmark-Generator
#4200 · Peiwen Yuan, Yiwei Li, Shaoxiong Feng, Xinglin Wang, Yueqi Zhang, Jiayi Shi, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

Poster Session 2

1 paper
Wednesday, December 3, 2025 · 4:30 PM → 7:30 PM
Exhibit Hall C,D,E
Stitch and Tell: A Structured Data Augmentation Method for Spatial Understanding
#1516 · Hang Yin, Xiaomin He, Peiwen Yuan, Yiwei Li, Jiayi Shi, Wenxiao Fan, Shaoxiong Feng, Kan Li

Poster Session 4

1 paper
Thursday, December 4, 2025 · 4:30 PM → 7:30 PM
Exhibit Hall C,D,E
Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play Modules
#3517 · Yueqi Zhang, Peiwen Yuan, Yiwei Li, Shaoxiong Feng, Xinglin Wang, Jiayi Shi, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

We formalise quoting in conversation, release a training set and benchmark, and introduce a tiny adapter that lets LLMs exploit quoted spans with zero prompt overhead.

Poster Session 5

1 paper
Friday, December 5, 2025 · 11:00 AM → 2:00 PM
Exhibit Hall C,D,E
Every Rollout Counts: Optimal Resource Allocation for Efficient Test-Time Scaling
#3518 · Xinglin Wang, Yiwei Li, Shaoxiong Feng, Peiwen Yuan, Yueqi Zhang, Jiayi Shi, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

We propose DORA, a provably optimal resource allocation strategy for efficient test-time scaling.