Xinchao Wang

AutoMIA introduces an agentic framework that automates the process of Membership Inference Attacks (MIAs) by self-exploring the attack space, achieving state-of-the-art performance without manual feature engineering.

dMoE proposes a block-level Mixture-of-Experts (MoE) framework for Diffusion Large Language Models (dLLMs) that aggregates token-level expert distributions into a unified block-level distribution, significantly reducing memory usage and improving inference speed.