Yimeng Zhang

Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs

Shop-R1: Rewarding LLMs to Simulate Human Behavior in Online Shopping via Reinforcement Learning

The Dual Power of Interpretable Token Embeddings: Jailbreaking Attacks and Defenses for Diffusion Model Unlearning

See, Think, Act: Online Shopper Behavior Simulation with VLM Agents

DeepZero: Scaling Up Zeroth-Order Optimization for Deep Model Training

Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models