Open to research collaboration Los Angeles · CA
GitHub ↗ Scholar ↗ LinkedIn ↗ CV ↗

I study multimodal reasoning, visual grounding, and continuous representations, with a broader interest in trustworthy AI and foundation model safety.

davidwei23@g.ucla.edu
Explore my work

Selected work

Publications

01
Chain-of-Visual-Thought framework diagram

ECCV · 2026

Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens

Yiming Qin, Bomin Wei, Jiaxin Ge, Konstantinos Kallidromitis, Stephanie Fu, Trevor Darrell, Xudong Wang

 02
Automated vulnerability repair timeline diagram

USENIX Security · 2025

SoK: Towards Effective Automated Vulnerability Repair

Ying Li, Faysal Hossain Shezan, Bomin Wei, Gang Wang, Yuan Tian

 03
DeepLPI model architecture diagram

Scientific Reports · 2022

DeepLPI: A Novel Deep Learning-Based Model for Protein–Ligand Interaction Prediction for Drug Repurposing

Bomin Wei, Yue Zhang, Xiang Gong