5 papers
Hierarchical Shared Memory-Aware Optimization for TRSM on GPU Platforms
Xinzhe Chen, Haowei Li, Lijuan Hu +2
Triangular Solve with Multiple Right-hand Sides (TRSM) is a fundamental BLAS Level-3 operation that underpins LU/Cholesky decomposition, sparse direct solvers, and matrix inversion…
LightEMMA: A Longitudinal Evaluation of Vision-Language Models for Autonomous Driving
Zhijie Qiao, Haowei Li, Zhong Cao +1
Rapid advances in vision-language models (VLMs) have generated growing interest in their application to autonomous driving. A prevailing assumption is that successive VLM generatio…
FedFQ: Federated Learning with Fine-Grained Quantization
Haowei Li, Weiying Xie, Hangyu Ye +3
Federated learning (FL) is a decentralized approach, enabling multiple participants to collaboratively train a model while ensuring the protection of data privacy. The transmission…
Reducing Spurious Correlation for Federated Domain Generalization
Shuran Ma, Weiying Xie, Daixun Li +2
The rapid development of multimedia has provided a large amount of data with different distributions for visual tasks, forming different domains. Federated Learning (FL) can effici…
Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks
Boheng Li, Yishuo Cai, Haowei Li +3
Model quantization is widely used to compress and accelerate deep neural networks. However, recent studies have revealed the feasibility of weaponizing model quantization via impla…