Welcome to my personal website! I’m Haizhou Shi (史海舟), a Fourth-year Ph.D. student in the CS Department at Rutgers University, advised by Prof. Hao Wang. My research focuses on developing reliable and efficient methods for adapting machine learning models. I’m currently exploring two main areas: uncertainty estimation in LLMs through Bayesian Deep Learning approaches and continual training of Large Language Models (LLMs) - including continued pre-training, post-training, and alignment.

Prior to Rutgers, I received my M.S. and B.S. degrees from the CS Department at Zhejiang University in 2022 and 2019, where I worked with Prof. Siliang Tang and Yueting Zhuang. My research there focused on developing generalizable representations across various learning paradigms, including unsupervised, weakly-supervised, federated, and continual learning.

News

• [09/2025] Our paper on Bayesian LLMs for Reasoning got accepted at NeurIPS 2025 FoRLM Workshop!
• [09/2025] Our paper on Bayesian LLMs got accepted at NeurIPS 2025!
• [05/2025] Our survey on Continual Learning of LLMs got accepted at CSUR!
• [05/2025] Our paper on LVLMs got accepted at ICML 2025!
• [01/2025] I will join Salesforce AI Reseach as a research intern in summer 2025!
• [01/2025] Our paper on LVLMs got accepted at NAACL 2025!
• [01/2025] I gave a talk on Bayesian Uncertainty Estimation for LLMs at Red Hat.
• [09/2024] Our paper on Bayesian LLMs got accepted at NeurIPS 2024!
• [01/2024] I will join Morgan Stanley ML Research as a research intern in summer 2024!
• [09/2023] Our paper on Continual Learning got accepted at NeurIPS 2023!
• [09/2022] I was fortunate to join Rutgers as a Ph.D. student, to work with Prof. Hao Wang!
• [02/2022] Our paper on Federated Learning got accepted at AAAI-FL-2022 workshop as oral presentation!
• [12/2021] Our paper on Representation Learning got accepted at AAAI 2022 as oral presentation (top ~1.6%)!

Selected Publications

(where selection is completely based on my own bias, and “*” denotes equal contribution)

TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning

Tunyu Zhang*, Haizhou Shi*, Yibin Wang, Hengyi Wang, Xiaoxiao He, Zhuowei Li, Haoxian Chen, Ligong Han, Kai Xu, Huan Zhang, Dimitris Metaxas, Hao Wang
NeurIPS Workshop: First Workshop on Foundations of Reasoning in Language Models, 2025.
[paper] [code]

Training-Free Bayesianization for Low-Rank Adapters of Large Language Models

Haizhou Shi*, Yibin Wang*, Ligong Han, Huan Zhang, Hao Wang
Thirty-Seventh Annual Conference on Neural Information Processing Systems (NeurIPS), 2025.
[paper] [code]

Continual Learning of Large Language Models: A Comprehensive Survey

Haizhou Shi, Zihao Xu, Hengyi Wang, Weiyi Qin, Wenyuan Wang, Yibin Wang, Zifeng Wang, Sayna Ebrahimi, Hao Wang
ACM Computing Surveys, 2025.
[paper] [code]

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering

Zhuowei Li, Haizhou Shi, Yunhe Gao, Di Liu, Zhenting Wang, Yuxiao Chen, Ting Liu, Long Zhao, Hao Wang, and Dimitris N. Metaxas
Forty-Second International Conference on Machine Learning (ICML), 2025.
[paper] [code]

Multimodal Needle in a Haystack: Benchmarking Long-Context Capability of Multimodal LLMs

Hengyi Wang, Haizhou Shi, Shiwei Tan, Weiyi Qin, Wenyuan Wang, Tunyu Zhang, Akshay Nambi, Tanuja Ganu, Hao Wang
Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL), 2025.
[paper] [code]

BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models

Yibin Wang*, Haizhou Shi*, Ligong Han, Dimitris Metaxas, Hao Wang
Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024.
[paper] [code] [slides] [talk]

A Unified Approach to Domain Incremental Learning with Memory: Theory and Algorithm

Haizhou Shi, Hao Wang
Thirty-Seventh Annual Conference on Neural Information Processing Systems (NeurIPS), 2023.
[paper] [code] [slides] [talk]