Nanowerk

When machine learning shows its reasoning, electrocatalyst discovery accelerates

Machine learning algorithms that output human-readable equations and design rules are transforming how electrocatalysts for ...

MIT's new fine-tuning method lets LLMs learn new skills without losing old ones

MIT researchers unveil a new fine-tuning method that lets enterprises consolidate their "model zoos" into a single, continuously learning agent.
IEEE

PowerDiffuser: Collaborative Contrastive-Reconstruction Self-Supervised Learning for Robust Power Load Signal Representation

Abstract: The widespread deployment of smart meters has created significant opportunities for applying artificial intelligence technologies to power system tasks. However, the high cost of data ...
EurekAlert!

Invariant graph learning meets information bottleneck for out-of-distribution generalization

Graph out-of-distribution (OOD) generalization remains a major challenge in graph neural networks (GNNs). Invariant learning, aiming to extract invariant features across varied distributions, has ...
Mirage News

Invariant Graph Learning Tackles OOD Generalization

Graph out-of-distribution (OOD) generalization remains a major challenge in graph neural networks (GNNs). Invariant learning, aiming to extract ...
GitHub

Self-supervised physics-informed generative networks for phase retrieval from a single X-ray hologram

Abstract: X-ray phase contrast imaging significantly improves the visualization of structures with weak or uniform absorption, broadening its applications across a wide range of scientific disciplines ...
IEEE

SCGRL: Graph representation learning based on edge structure contrastive self-supervised framework

Abstract: In recent years, significant advancements have been made in contrastive self-supervised learning for graphs. However, most of the existing methods start from the feature level and ignore the ...