Chuhan Li

Chuhan Li 黎楚涵 Ph.D. Student @UCSB NLP Group
University of California, Santa Barbara

Email: chuhan_li [at] ucsb [dot] edu

LinkedIn / Google Scholar / GitHub / X (Twitter)

I am a first year Ph.D. student in Computer Science at UC Santa Barbara, advised by Prof. Xin (Eric) Wang.

My research goal is to develop intelligent systems that reason and interact with the physical world. My primary focus lies in machine learning, natural language processing, and computer vision, particularly in spatial intelligence, multimodal reasoning, and neuro-symbolic reasoning. My recent research interests include:

Evaluation and Analysis of spatial-temporal capabilities in foundation models
Post-Training and Agentic Systems for enhancing spatial understanding and reasoning
Robot Learning for human interaction in the real world

Before UC Santa Barbara, I received my Master's degree at Yale University, advised by Prof. Arman Cohan and Prof. Rex Ying, where I worked on formal reasoning, multimodal reasoning, and evaluation; and my Bachelor's degree at Boston University, advised by Prof. Evimaria Terzi, where I worked on combinatorial optimization and algorithmic data mining.

News

Mar 2026	Excited to share that I'll be joining Amazon FAR (Frontier AI & Robotics) as an Applied Scientist Intern in this summer!
Feb 2026	New preprint: Learning Situated Awareness in the Real World is now available on arXiv!
May 2025	Graduated from Yale University and will start my PhD at UCSB NLP Group!
Jan 2025	Our paper 🍅 TOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation Models has been accepted by ICLR 2025! Let's catch up in Singapore 🇸🇬!
Sep 2024	Our paper M3SciQA: A Multi-Modal Multi-Document Scientific QA Benchmark for Evaluating Foundation Models has been accepted by EMNLP 2024 Findings! Let's catch up in Miami 🌴!
Sep 2023	Started my Master at Yale University!

Selected Publications

* indicates equal contribution.

Learning Situated Awareness in the Real World
Chuhan Li, Ruilin Han, Joy Hsu, Yongyuan Liang, Rajiv Dhawan, Jiajun Wu, Ming-Hsuan Yang, and Xin (Eric) Wang
Preprint
Project Page / Paper / Dataset / X (Twitter)

🍅 TOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation Models
Ziyao Shangguan*, Chuhan Li*, Yuxuan Ding, Yanan Zheng, Yilun Zhao, Tesca Fitzgerald, and Arman Cohan
ICLR 2025
Paper / Code / Dataset / Poster

HybridMind: Meta Selection of Natural Language and Symbolic Language for Enhanced LLM Reasoning
Simeng Han*, Tianyu Liu*, Chuhan Li*, Xuyuan Xiong, and Arman Cohan
XLLM-Reason-Plan COLM Workshop 2025
Paper

M3SciQA: A Multi-Modal Multi-Document Scientific QA Benchmark for Evaluating Foundation Models
Chuhan Li*, Ziyao Shangguan*, Yilun Zhao, Deyuan Li, Yixin Liu, and Arman Cohan
EMNLP Findings 2024
Paper / Code

Teaching

	Teaching Assistant, Introduction to Machine Learning (CMPSC 165B), Winter 2026
	Teaching Assistant, Natural Language Processing (CPSC 477/577), Spring 2025 Teaching Assistant, Deep Learning on Graph-Structured Data (CPSC 483/583), Fall 2024 Teaching Assistant, Introduction to Machine Learning (CPSC 381), Spring 2024 Teaching Assistant, Algorithms (CPSC 365), Fall 2023
	Teaching Assistant, Combinatoric Structures (CS 131), Fall 2021, Spring 2022, Spring 2023 Teaching Assistant, Foundation of Data Science (CS 365), Fall 2022

Professional Services

Conference Reviewer:

International Conference on Learning Representations (ICLR): 2025, 2026
International Conference on Machine Learning (ICML): 2026
Conference on Neural Information Processing Systems (NeurIPS): 2026
ACL Rolling Review (ARR): 2024, 2025, 2026

Workshop Organizer:

England NLP (NENLP) Workshop 2025 — Program Chair