Yang Bai

Explore Data Left Behind in Reinforcement Learning for Reasoning Language Models

AgenticPA: Toward Automated and Large-Scale Prompt Attacks on LLMs

Why does Weak-OOD Help? A Further Step Towards Understanding Jailbreaking VLMs

OT-Attack: Enhancing Adversarial Transferability of Vision-Language Models via Optimal Transport Optimization

Image-level Memorization Detection via Inversion-based Inference Perturbation