Zhi Tang

Attention Misalignment Attacks: Targeting Cross-Modal Attention in Multimodal Large Language Models for Adversarial Examples

DocRobust: Enhancing Robustness of Multi-modal LLMs in Low-Quality Document Image Scenarios

An Efficient Subgraph GNN with Provable Substructure Counting Power

Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts