Meta launches image generation model with coding, search capabilities

Meta Platforms Inc. today debuted an image generation model that can write code and search the web. Muse Image is the second ...
GitHub

Dense reinforcement learning for safety validation of autonomous vehicles

This project contains the source code and data for the paper titled "Dense reinforcement learning for safety validation of autonomous vehicles". Feng, S., Sun, H ...
Aalto University

Doctoral Researcher in AI and Quantum-Inspired Optimization for Sustainable Energy Systems

Are you passionate about developing AI-based and quantum-inspired solutions for the next generation of sustainable energy systems? We are now looking for a fully funded Doctoral Researcher to work on ...
IEEE

Control Strategy of Hard Shoulder Running at Intelligent Freeway Merging Areas Based on Deep Reinforcement Learning

Abstract: The hard shoulder running (HSR) strategy has proven to be an effective measure to alleviate freeway traffic congestion. This paper proposes a smart HSR strategy based on deep reinforcement ...
techtimes

Open-Source Coding Model Ornith-1.0 Writes Its Own Training Scaffold in Reinforcement Learning

DeepReinforce today released Ornith-1.0, a family of open-source coding models built around a mechanism most RL-trained agents avoid: the model itself writes the training harness that guides its own ...
eLife

Neural signatures of model-based and model-free reinforcement learning across prefrontal cortex and striatum

This important study presents single-unit activity collected during model-based (MB) and model-free (MF) reinforcement learning in non-human primates. The dataset was carefully collected, and the ...

Why Weibo’s tiny VibeThinker-3B has the AI world arguing over benchmarks again

B, a 3-billion-parameter AI model, is challenging OpenAI, Google and DeepSeek on math and coding benchmarks while reigniting the debate over AI scaling, benchmark gaming and small-model reasoning.
GitHub

Train multi-step agents for real-world tasks using GRPO.

W&B Training (Serverless RL) is the first publicly available service for flexibly training models with reinforcement learning. It manages your training and inference infrastructure automatically, ...