Zhuowei Li

Researcher, Amazon

Joined

February 2020

Names

Zhuowei Li (Preferred)

Emails

****@sensetime.com (Confirmed)

****@columbia.edu (Confirmed)

****@cs.rutgers.edu (Confirmed)

****@scarletmail.rutgers.edu (Confirmed)

****@icloud.com (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Researcher

Amazon (amazon.com)

2025 – Present

PhD student

Rutgers University, New Brunswick (cs.rutgers.edu)

2021 – 2025

Researcher

SenseTime (sensetime.com)

2019 – 2021

MS student

Columbia University (columbia.edu)

2017 – 2019

Advisors, Relations & Conflicts

PhD Advisor

Dimitris N. Metaxas

2021 – 2025

Expertise

LLM/LVLM

In-context Learning

2023 – Present

Computer Vision

2019 – Present

Medical Image Analysis

2019 – Present

Continual Learning

2022 – 2024

Publications

Visual Sparse Steering (VS2): Unsupervised Adaptation for Image Classification via Sparsity-Guided Steering Vectors
Gerasimos Chatzoudis, Zhuowei Li, Gemma Elyse Moran, Hao Wang, Dimitris N. Metaxas
- Submitted to ICLR 2026
- Readers: Everyone
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 N. Metaxas, Hao Wang
- ICLR 2026 Poster
- Readers: Everyone
TokUR: Token-Level Uncertainty Estimation for Large Language Mode Reasoning
Tunyu Zhang, Haizhou Shi, Yibin Wang, Hengyi Wang, Xiaoxiao He, Zhuowei Li, Haoxian Chen, Ligong Han, Kai Xu, Huan Zhang, Dimitris N. Metaxas, Hao Wang
- FoRLM 2025
- Readers: Everyone
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, Dimitris N. Metaxas
- OpenReview Archive Direct Upload
- Readers: Everyone
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, Dimitris N. Metaxas
- ICML 2025 poster
- Readers: Everyone
Implicit In-context Learning
Zhuowei Li, Zihao Xu, Ligong Han, Yunhe Gao, Song Wen, Di Liu, Hao Wang, Dimitris N. Metaxas
- ICLR 2025 Poster
- Readers: Everyone
Steering Prototypes with Prompt Tuning for Rehearsal-free Continual Learning
Zhuowei Li, Long Zhao, Zizhao Zhang, Han Zhang, Ting Liu, Dimitris N. Metaxas
- 22 Sept 2022 (modified: 13 Feb 2023)
- ICLR 2023 Conference Withdrawn Submission
- Readers: Everyone
Contrastive and Selective Hidden Embeddings for Medical Image Segmentation
Zhuowei Li, Zihao Liu, Zhiqiang Hu, Qing Xia, Ruiqin Xiong, Shaoting Zhang, Dimitris N. Metaxas, Tingting Jiang
- 2022 (modified: 01 Nov 2022)
- CoRR 2022
- Readers: Everyone
Towards Self-supervised and Weight-preserving Neural Architecture Search
Zhuowei Li, Yibo Gao, Zhenzhou Zha, Zhiqiang Hu, Qing Xia, Shaoting Zhang, Dimitris N. Metaxas
- 2022 (modified: 01 Nov 2022)
- CoRR 2022
- Readers: Everyone
Self-Ensembling Contrastive Learning for Semi-Supervised Medical Image Segmentation
Jinxi Xiang, Zhuowei Li, Wenji Wang, Qing Xia, Shaoting Zhang
- 2021 (modified: 01 Nov 2022)
- CoRR 2021
- Readers: Everyone

View all 14 publications

Co-Authors

View all 46 co-authors