Researchers double AI training speed just by reclaiming idle GPU time

A team of researchers from MIT, working with collaborators including NVidia, says it has found a surprisingly practical way to reclaim wasted compute during training — in some cases cutting overall ...
Fabbaloo

Reinforcement Learning Tames DLP Peel Forces For Fragile Prints

A new research paper proposes geometry adaptive reinforcement learning to reduce peel forces in Digital Light Processing (DLP) resin printing to save fragile features and increase lift success for ...

This doctor is training AI to do her job. And it’s a booming business

AI models are trained on massive amounts of data. But that training doesn’t do much good without what’s known as “reinforcement learning,” a process that involves human experts teaching models the ...
techxplore

Why reinforcement learning breaks at scale, and how a new method fixes it

From autonomous cars to video games, reinforcement learning (machine learning through interaction with environments) can have an important impact. That may feel especially true, for example, when ...
Microsoft

Multimodal reinforcement learning with agentic verifier for AI agents

Over the past few years, AI systems have become much better at discerning images, generating language, and performing tasks within physical and virtual environments. Yet they still fail in ways that ...
VentureBeat

Why reinforcement learning plateaus without representation depth (and other key takeaways from NeurIPS 2025)

Every year, NeurIPS produces hundreds of impressive papers, and a handful that subtly reset how practitioners think about scaling, evaluation and system design. In 2025, the most consequential works ...
GitHub

reinforcement-learning

A library of enterprise-grade AI agents designed to democratize artificial intelligence and provide free, open-source alternatives to overvalued Y Combinator startups. If you are excited about ...
VentureBeat

Google’s new AI training method helps small models tackle complex reasoning

Researchers at Google Cloud and UCLA have proposed a new reinforcement learning framework that significantly improves the ability of language models to learn very challenging multi-step reasoning ...
The Robot Report

AgiBot deploys its Real-World Reinforcement Learning system

AgiBot announced a key milestone this week with the successful deployment of its Real-World Reinforcement Learning system in a manufacturing pilot with Longcheer Technology. The pilot project marks ...
marktechpost

Google AI Unveils Supervised Reinforcement Learning (SRL): A Step Wise Framework with Expert Trajectories to Teach Small Language Models to Reason through Hard Problems

How can a small model learn to solve tasks it currently fails at, without rote imitation or relying on a correct rollout? A team of researchers from Google Cloud AI Research and UCLA have released a ...