3 papers
cs.AI2025
A Guardrail for Safety Preservation: When Safety-Sensitive Subspace Meets Harmful-Resistant Null-Space
Bingjie Zhang, Yibo Yang, Zhe Ren +4
Large language models (LLMs) have achieved remarkable success in diverse tasks, yet their safety alignment remains fragile during adaptation. Even when fine-tuning on benign data o…
cs.LG2025
Merging Smarter, Generalizing Better: Enhancing Model Merging on OOD Data
Bingjie Zhang, Hongkang Li, Changlong Shi +5
Multi-task learning (MTL) concurrently trains a model on diverse task datasets to exploit common features, thereby improving overall performance across the tasks. Recent studies ha…
cs.LG2025
FedAWA: Adaptive Optimization of Aggregation Weights in Federated Learning Using Client Vectors
Changlong Shi, He Zhao, Bingjie Zhang +3
Federated Learning (FL) has emerged as a promising framework for distributed machine learning, enabling collaborative model training without sharing local data, thereby preserving…