News
Ex-OpenAI CTO Mira Murati’s $12B startup fixes AI’s reproducibility bug, solving nondeterminism in LLMs with open-source batch-invariant kernels.
A growing number of AI processors are being designed around specific workloads rather than standardized benchmarks, ...
Abstract: Code search is a vital activity in software engineering, focused on identifying and retrieving the correct code snippets based on a query provided in natural language. Approaches based on ...
CL-GNN: Contrastive Learning and Graph Neural Network for Protein–Ligand Binding Affinity Prediction
Department of Chemical Engineering and Technology, College of Materials Science and Engineering, Beijing University of Technology, Beijing 100124, P. R. China ...
Abstract: Code search aims to retrieve the code snippet that highly matches the given query described in natural language. Recently, many code pre-training approaches have demonstrated impressive ...
In a distributed computing environment, the computation of loss functions that are separable can be performed locally on each GPU(e.g. cross entropy). This local computation covers the entire loss ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback