AI captures particle accelerator behavior to optimize machine performance

Keeping high-power particle accelerators at peak performance requires advanced and precise control systems. For example, the primary research machine at the U.S. Department of Energy's Thomas ...

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.

TTT-Discover optimizes GPU kernels 2x faster than human experts — by training during inference

A new technique from Stanford, Nvidia, and Together AI lets models learn during inference rather than relying on static ...
Tech Xplore

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 ...
IEEE

Reinforcement Learning-Based Adaptive Finite-Time Performance Constraint Control for Nonlinear Systems

Abstract: This article focuses on the issue of reinforcement learning (RL)-based adaptive optimal finite-time performance constraint control for nonlinear systems. By the aid of RL-based critic-actor ...
marktechpost

Microsoft AI Introduces rStar2-Agent: A 14B Math Reasoning Model Trained with Agentic Reinforcement Learning to Achieve Frontier-Level Performance

Large language models have made impressive strides in mathematical reasoning by extending their Chain-of-Thought (CoT) processes—essentially “thinking longer” through more detailed reasoning steps.
Scientific Research Publishing

Ribba, B. (2023) Reinforcement Learning as an Innovative Model-Based Approach: Examples from Precision Dosing, Digital Health and Computational Psychiatry. Frontiers in ...

ABSTRACT: Depression treatment often involves a complex and lengthy trial-and-error process, where clinicians sequentially prescribe medications to identify the most ...
Seeking Alpha

Braze, Inc. (BRZE) Q1 2026 Earnings Call Transcript

Welcome to the Braze Fiscal First Quarter 2026 Earnings Conference Call. My name is Luke, and I'll be your operator for today's call. [Operator Instructions] I'll now turn the call over to Christopher ...
GitHub

Reinforcement Learning for Reasoning in Large Language Models with One Training Example

Our training pipeline is adapted from verl and rllm(DeepScaleR). The installation commands that we verified as viable are as follows: conda create -y -n rlvr_train ...
marktechpost

LLMs Can Learn Complex Math from Just One Example: Researchers from University of Washington, Microsoft, and USC Unlock the Power of 1-Shot Reinforcement Learning with ...

Recent advancements in LLMs such as OpenAI-o1, DeepSeek-R1, and Kimi-1.5 have significantly improved their performance on complex mathematical reasoning tasks. Reinforcement Learning with Verifiable ...