When Do We Need On-Policy Distillation? Distilling on Offline Student Rollouts Is Often Better Paper • 2610.11291 • Published 10 days ago • 23
When Do We Need On-Policy Distillation? Distilling on Offline Student Rollouts Is Often Better Paper • 2610.11291 • Published 10 days ago • 23
Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents Paper • 2609.39982 • Published 18 days ago • 119
Nemotron-Flash Collection A hybrid small language model family designed around real-world latency. • 4 items • Updated 30 days ago • 2
Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients Paper • 2606.18216 • Published Jun 16 • 65
Agent Explorative Policy Optimization for Multimodal Agentic Reasoning Paper • 2605.28774 • Published May 27 • 90
view article Article Towards Speed-of-Light Text Generation with Nemotron-Labs Diffusion Language Models nvidia • May 23 • 36
view article Article Towards Speed-of-Light Text Generation with Nemotron-Labs Diffusion Language Models nvidia • May 23 • 36
Nemotron-Labs-Diffusion Collection A Tri-Mode Language Model Family Unifying Autoregressive, Diffusion, and Self-Speculation Decoding • 7 items • Updated Aug 11 • 56