GitHub

verl: Volcano Engine Reinforcement Learning for LLMs

verl is a flexible, efficient and production-ready RL training library for large language models (LLMs). verl is the open-source version of HybridFlow: A Flexible and Efficient RLHF Framework paper.
pv magazine International

US researchers use machine learning to detect hidden solar array defects

Researchers from Stony Brook University, in collaboration with Ecosuite and Ecogy Energy, have developed a self-supervised machine-learning algorithm designed to identify physical anomalies in solar ...
Microsoft

Agent Lightning: Adding reinforcement learning to AI agents without code rewrites

AI agents are reshaping software development, from writing code to carrying out complex instructions. Yet LLM-based agents are prone to errors and often perform poorly on complicated, multi-step tasks ...
IEEE

Transfer Learning for RCS Reduction of Antenna Arrays Across Arbitrary Frequency Bands

Abstract: Recent studies reveal that deep learning networks can reduce the radar cross section (RCS) of antenna arrays. However, the existing deep learning networks are all for a fixed frequency band.
IEEE

Spatio-temporal learning with arrays of analog nanosynapses

Abstract: Emerging nanodevices such as resistive memories are being considered for hardware realizations of a variety of artificial neural networks (ANNs), including highly promising online variants ...