activity
20242026
collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

Effective MoE-based LLM Compression by Exploiting Heterogeneous Inter-Group Experts Routing Frequency and Information Density

Zhendong Mi, Yixiao Chen, Pu Zhao +4

Mixture-of-Experts (MoE) based Large Language Models (LLMs) have achieved superior performance, yet the massive memory overhead caused by storing multiple expert networks severely…

cs.LG2025

Pruning and Malicious Injection: A Retraining-Free Backdoor Attack on Transformer Models

Taibiao Zhao, Mingxuan Sun, Hao Wang +2

Transformer models have demonstrated exceptional performance and have become indispensable in computer vision (CV) and natural language processing (NLP) tasks. However, recent stud…

cs.LG2025

Towards Interpretable Adversarial Examples via Sparse Adversarial Attack

Fudong Lin, Jiadong Lou, Hao Wang +2

Sparse attacks are to optimize the magnitude of adversarial perturbations for fooling deep neural networks (DNNs) involving only a few perturbed pixels (i.e., under the l0 constrai…

cs.LG2025

Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity

Yide Ran, Wentao Guo, Jingwei Sun +7

Federated Learning enables collaborative fine-tuning of Large Language Models (LLMs) across decentralized Non-Independent and Identically Distributed (Non-IID) clients, but such mo…

cs.LG2025

An Empirical Study of the Impact of Federated Learning on Machine Learning Model Accuracy

Haotian Yang, Zhuoran Wang, Benson Chou +4

Federated Learning (FL) enables distributed ML model training on private user data at the global scale. Despite the potential of FL demonstrated in many domains, an in-depth view o…

cs.LG2024

Learning Unlabeled Clients Divergence for Federated Semi-Supervised Learning via Anchor Model Aggregation

Marawan Elbatel, Hualiang Wang, Jixiang Chen +2

Federated semi-supervised learning (FedSemi) refers to scenarios where there may be clients with fully labeled data, clients with partially labeled, and even fully unlabeled client…