Bo Hui

Weak-to-Strong Generalization with Failure Trajectories

Forget Many, Forget Right: Scalable and Precise Concept Unlearning in Diffusion Models

Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron Masking

Your Language Model Secretly Contains Personality Subnetworks

From Bits to Chips: An LLM-based Hardware-Aware Quantization Agent for Streamlined Deployment of LLMs

LightCache: Memory-Efficient, Training-Free Acceleration for Video Generation

The Right to be Forgotten in Pruning: Unveil Machine Unlearning on Sparse Models

Towards Distributed Backdoor Attacks with Network Detection in Decentralized Federated Learning

Towards Building Reliable Conditional Diffusion Models for Protein Generation

Optimal Client Training in Federated Learning with Deep Reinforcement Learning