EurekAlert!

Missing data recovery for heterogeneous graphs with incremental multi-source data fusion

Heterogeneous graphs organize data with nodes and edges, and have been widely used in various graph-centric applications.
The Next Platform

Cerebras Inks Transformative $10 Billion Inference Deal With OpenAI

If GenAI is going to go mainstream and not just be a bubble that helps prop up the global economy for a couple of years, AI ...
GitHub

Retraining-Free Merging of Sparse Mixture-of-Experts via Hierarchical Clustering

In this work, we propose HC-SMoE (Hierarchical Clustering for Sparsely activated Mixture of Experts), a task-agnostic expert merging framework that reduces SMoE model parameters without retraining.
GitHub

[QUESTION] Slow pretraining performance for MoE model on HPC cluster with A100 GPUs

Is this training speed normal? Am I making some big mistakes? I am experiencing slow pretraining performance while training a Mixture-of-Experts (MoE) LLM using Megatron-LM on a HPC cluster with ...
IEEE

A Rapid Radar Signal Sorting Method Based on Density and Gaussian Mixture Model Data Stream Clustering

Abstract: Radar signal sorting is one of the crucial techniques in radar reconnaissance. However, as the electromagnetic environment increasingly complex and the density of radar pulses surges, the ...
marktechpost

NVIDIA Introduces CLIMB: A Framework for Iterative Data Mixture Optimization in Language Model Pretraining

As large language models (LLMs) scale in size and capability, the choice of pretraining data remains a critical determinant of downstream performance. Most LLMs are trained on large, web-scale ...
C&EN

Phase Separation Clustering of Poly Ubiquitin Cargos on Ternary Mixture Lipid Membranes by Synthetically Cross-Linked Ubiquitin Binder Peptides

Creative Commons (CC): This is a Creative Commons license. Attribution (BY): Credit must be given to the creator. Ubiquitylation is involved in various physiological processes, such as signaling and ...
IEEE

Enhancing Cluster Accuracy in Diabetes Multimorbidity With Dirichlet Process Mixture Models

Abstract: Clustering of diabetic multimorbidity data from EHRs is challenging due to patient heterogeneity, high-dimensional variables, sensitivity to parameter settings, and high computational ...