Haibing Guan

FedMomentum: Preserving LoRA Training Momentum in Federated Fine-Tuning

Excavating Consistency Across Editing Steps for Effective Multi-Step Image Editing

POLAR: Policy-based Layerwise Reinforcement Learning for Stealthy Backdoor Attacks in Federated Learning

Offline Reinforcement Learning via Action-Space Pseudo-Labeling

Bridging the Gap Between Zeroth-Order and First-Order Fine-Tuning via Dynamic Adaptive Subspace Pre-tuning

$STRCMP$: Integrating Graph Structural Priors with Language Models for Combinatorial Optimization

Poisoning with A Pill: Circumventing Detection in Federated Learning

Exploring Diffusion Models' Corruption Stage in Few-Shot Fine-tuning and Mitigating with Bayesian Neural Networks