5 papers · 1 filter
FedFFT: Taming Client Drift in Federated SAM via Spectral Perturbation Filtering
Liyang Yuan, Yibo Yang, Dandan Guo
Federated Learning (FL) enables decentralized training without data sharing, but suffers from statistical heterogeneity across clients, leading to client drift, poor generalization…
GateMem: Benchmarking Memory Governance in Multi-Principal Shared-Memory Agents
Zhe Ren, Yibo Yang, Yimeng Chen +7
Memory benchmarks for LLM agents largely assume single-user settings, leaving shared assistants for hospitals, workplaces, campuses, and households understudied. In these deploymen…
Safeguarding LLM Fine-tuning via Push-Pull Distributional Alignment
Haozhong Wang, Zhuo Li, Yibo Yang +3
The inherent safety alignment of Large Language Models (LLMs) is prone to erosion during fine-tuning, even when using seemingly innocuous datasets. While existing defenses attempt…
Deep Neural Network Calibration by Reducing Classifier Shift with Stochastic Masking
Jiani Ni, He Zhao, Yibo Yang +1
In recent years, deep neural networks (DNNs) have shown competitive results in many fields. Despite this success, they often suffer from poor calibration, especially in safety-crit…
Lifted Hybrid Variational Inference
Yuqiao Chen, Yibo Yang, Sriraam Natarajan +1
A variety of lifted inference algorithms, which exploit model symmetry to reduce computational cost, have been proposed to render inference tractable in probabilistic relational mo…