nvidia/Nemotron-RL-Agentic-Conversational-Tool-Use-Seed-v1 Viewer • Updated 4 days ago • 100k • 361 • 3
view article Article Score Function Centering: Your Stale Rollout Does Not Have to Be Importance Sampled and Stabilize Your Async RL Training with Trainer-Generator KL NormalUhr • 2 days ago • 1
view article Article The Most Intuitive Way to Understand Score Function Centering: Understand Trainer-Generator Mismatch in Async RL from the Score Function NormalUhr • 3 days ago • 6
OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding Paper • 2610.18829 • Published 6 days ago • 579
nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16 Image-Text-to-Text • 75B • Updated 2 minutes ago • 1.7k • 37
Muse Spark Open Collection Muse Spark Open model. A 816B parameter model with 42B Active parameters. BF16 and NVFP4 Weights. • 2 items • Updated 3 days ago • 151
VEPA: Verified Evolving Formal Policy for Lifelong LLM Agent Guardrails Paper • 2610.12813 • Published 11 days ago • 2