I'm a 4th year undergraduate at Columbia University. I'm interested in the potential in building a robust, genuine intelligence in AI, with a focus on multimodal systems that can generalize, adapt, and support personalized users and needs. Advised by Micah Goldblum & Julia Hirschberg.

Current Research Interests
[0001]
Applied machine learning
[0002]
Trust & robustness in human-centered AI
[0003]
Uni/multimodal reasoning strategies

Publications

2026
ULT

AI-Generated Patients Are Flawed Proxies of Realism

Charles Wang*, Cady Chen*
Preprint
paper
2026
Zebra-CoT

Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning

Ang Li*, Charles Wang*, Kaiyu Yue*, Zikui Cai*, Ollie Liu*, Deqing Fu*, Peng Guo*, Wang Bill Zhu*, Vatsal Sharan, Robin Jia, Willie Neiswanger, Furong Huang, Tom Goldstein, and Micah Goldblum
ICLR 2026
paper code dataset
2026
MI9

MI9: An Integrated Runtime Governance Framework for Agentic AI

Charles Wang*, Trisha Singhal*, Ameya Kelkar, Jason Tuo
AAAI 2026 TrustAgent Workshop
paper code
2025
ULT

On The Statistical Limits of Self-Improving Agents

Charles Wang*, Keir Dorchen*, Peter Jin
Preprint
paper code
2025
MathBode

MathBode: Measuring the Stability of LLM Reasoning using Frequency Response

Charles Wang
NeurIPS 2025 Math-AI Workshop
paper code dataset