today local_bar

Changqing Zhang

Full Professor, Tianjin University

2 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 6

Friday, December 5, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization

#3718 Spotlight · Qingyang Zhang, Haitao Wu, Changqing Zhang, Peilin Zhao, Yatao Bian

We makes an early attempt at fully unsupervised LLM reasoning incentivization.

DOTA: Distributional Test-time Adaptation of Vision-Language Models

#602 · Zongbo Han, Jialong Yang, Guangyu Wang, Junfan Li, Qianli Xu, Mike Zheng Shou, Changqing Zhang

We proposes a new Distributional Test-time Adaptation (DOTA) method, which continuously estimates the distribution of test samples.