Deep learning creates virtual multiplexed immunostaining to improve cancer diagnosis

Researchers at the University of California, Los Angeles (UCLA), in collaboration with pathologists from Hadassah Hebrew ...
IEEE

Efficient Multi-label Feature Selection via High-order Structure Information

Abstract: Multi-label feature selection (MFS) aims to select effective features that can be associated with multiple class labels. However, existing MFS methods usually constrain the feature selection ...
IEEE

Learning With Partial-Label and Unlabeled Data: Contrastive With Negative Example Separation

Abstract: Semi-Supervised Partial Label Learning (SSPLL) is an important branch of weakly supervised learning, where the data consists of both partial label examples and unlabeled ones. In SSPLL, the ...
GitHub

CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning

CUDA-L2 is a system that combines large language models (LLMs) and reinforcement learning (RL) to automatically optimize Half-precision General Matrix Multiply (HGEMM) CUDA kernels. CUDA-L2 ...
Microsoft

Rethinking Machine Learning Collective Communication as a Multi Commodity Flow problem

Cloud operators utilize collective communication optimizers to enhance the efficiency of the single-tenant, centrally managed training clusters they manage. However, current optimizers struggle to ...