Daizong Liu

Spotlight on Token Perception for Multimodal Reinforcement Learning

Multi-Layer Diffusion Strategy for Multi-IP Interaction-Aware Human Erasing

FrameThinker: Learning to Think with Long Videos via Multi-Turn Frame Spotlighting

Causal-CoT: Causal Chain-of-Thought for Validated Reasoning

An Image Is Worth Ten Thousand Words: Verbose-Text Induction Attacks on VLMs

Self-Reflective Reinforcement Learning for Diffusion-based Image Reasoning Generation

Towards Building Model/Prompt-Transferable Attackers against Large Vision-Language Models

Fit the Distribution: Cross-Image/Prompt Adversarial Attacks on Multimodal Large Language Models

Does Your Video-language Model Actually Understand the Language Input?

DEAL: High-Efficacy Privacy Attack on Retrieval-Augmented Generation Systems via LLM Optimizer

Can't See the Wood for the Trees: Can Visual Adversarial Patches Fool Hard-Label Large Vision-Language Models?

Strategy-centric Synthesis: Connecting Billions of Image-Text Pairs to High-Quality Visual Instruction Data

Are Large Vision-Language Models Robust to Adversarial Visual Transformations?