Zongxing Xie

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Constitutional AI & AI Ethics (1)Multimodal Models (1)Red-Teaming & Adversarial Robustness (1)

Frequent co-authors

Md Abdullahil Oaphy (1)Anhao Xiang (1)Huayue Gu (1)Chen-Yu Wang (1)

Papers (1)

Aug 18, 2026

Md Abdullahil Oaphy +51w ago

COMIC: Reference-Aware Safety Gating for Multimodal Large Language Models

MLLMs can be tricked into unsafe behavior by seemingly harmless prompts and images, but COMIC effectively mitigates this risk by focusing on the operation-target relationship.

Md Abdullahil Oaphy, Anhao Xiang, Zongxing Xie +3

Constitutional AI & AI Ethics Multimodal Models Red-Teaming & Adversarial Robustness

Search

Zongxing Xie

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)