NeoMME: A Single-Tower Multimodal-Native Multilingual Foundation Encoder for Efficient Fine-Tuning and Inference Paper • 2609.01657 • Published Aug 31 • 36
SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models Paper • 2609.02886 • Published Sep 2 • 118
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness? Paper • 2609.01437 • Published Sep 1 • 567
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills Paper • 2609.02749 • Published Sep 2 • 408
Rethinking On-Policy Distillation of Large Language Models II: One Training Example Paper • 2609.04172 • Published Sep 3 • 104
nvidia/Nemotron-RL-Instruction-Following-Structured-Outputs-v2 Viewer • Updated 7 days ago • 62.7k • 996 • 8
Nemotron-Post-Training-v3 Collection Collection of datasets used in the post-training phase of Nemotron Nano, Super, and Ultra v3. • 50 items • Updated Aug 11 • 203
view article Article ⚡ nano-vLLM: Lightweight, Low-Latency LLM Inference from Scratch zamal • Jun 28, 2025 • 48
Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architecture Problems Paper • 2607.21503 • Published Jul 23 • 29
Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning Paper • 2607.21653 • Published Jul 22 • 34
DataPrep-Bench: Benchmarking LLMs as Training Data Preparators Paper • 2607.20465 • Published May 19 • 56