Score Centering Stabilizes Off-policy Reinforcement Learning Paper • 2609.20807 • Published Sep 17 • 10
Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090 Paper • 2608.27370 • Published Aug 27 • 41
ServiceNow/PrivacyAlign-Nemotron-3-Nano-4B-Annotation-Conditioned-Reward Text Generation • Updated Jun 24 • 52 • 1
Apriel-Reasoner: RL Post-Training for General-Purpose and Efficient Reasoning Paper • 2604.02007 • Published Apr 2 • 13
CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents Paper • 2603.24440 • Published Mar 25 • 96
CohereLabs/cohere-transcribe-03-2026 Automatic Speech Recognition • 2B • Updated Oct 7 • 88.3k • • 1.25k