Publications

Yifan Sun
Equal contribution
, Jingyan Shen
Equal contribution
, Yibin Wang
Equal contribution
, Tianyu Chen, Zhendong Wang, Mingyuan Zhou, Huan Zhang (2025). Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay. NeurIPS 2025.
arxiv PDF
Tunyu Zhang
Equal contribution
, Haizhou Shi
Equal contribution
, Yibin Wang, Hengyi Wang, Xiaoxiao He, Zhuowei Li, Haoxian Chen, Ligong Han, Kai Xu, Huan Zhang, Dimitris Metaxas, Hao Wang (2025). TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning. ICLR 2026.
arxiv PDF
Haizhou Shi
Equal contribution
, Yibin Wang
Equal contribution
, Ligong Han, Dimitris Metaxas, Huan Zhang, Hao Wang (2024). Training-Free Bayesianization for Low-Rank Adapters of Large Language Models. NeurIPS 2025.
arxiv Code PDF Poster
Yibin Wang
Equal contribution
, Haizhou Shi
Equal contribution
, Ligong Han, Dimitris Metaxas, Hao Wang (2024). BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models. NeurIPS 2024.
arxiv NeurIPS Code PDF Poster Slides
Haizhou Shi, Zihao Xu, Hengyi Wang, Weiyi Qin, Wenyuan Wang, Yibin Wang, Zifeng Wang, Sayna Ebrahimi, Hao Wang (2024). Continual learning of large language models: A comprehensive survey. ACM Computing Surveys.
Link PDF
Yibin Wang
Equal contribution
, Yichen Yang
Equal contribution
, Di He, Kun He (2023). Robustness-Aware Word Embedding Improves Certified Robustness to Adversarial Word Substitutions. Findings of ACL 2023.
ACL Anthology Code PDF