R^2Orch: Recursive Self-Improvement for Agent Orchestration via Self-Play within a Skill-Internalization Loop Paper • 2610.22740 • Published 28 days ago • 49
Running on CPU Upgrade 744 The Ultimate MoE Training Handbook 🧩 744 A hands-on guide to training Mixture-of-Experts models
nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B Automatic Speech Recognition • 34B • Updated 20 days ago • 87.7k • • 3.4k
Running on Zero Agents Featured 511 Unlimited OCR 🏆 511 Extract text from images or PDFs with real-time streaming OCR