AgentBaton: Efficient Model Collaboration in Agentic Tasks Paper • 2610.35959 • Published 17 days ago • 20
Score Centering Stabilizes Off-policy Reinforcement Learning Paper • 2609.20807 • Published Sep 17 • 10
Building Auditable AI Text Detectors with Sparse Autoencoders Paper • 2610.30006 • Published 21 days ago • 14
Reading, Writing, Sharing, and Interacting with the World through Video Paper • 2610.31668 • Published 20 days ago • 43
NVIDIA Nemotron v3 Collection Open, Production-ready Enterprise Models • 46 items • Updated 18 days ago • 394
view article Article Train in Simulation, Deploy on a Real Robot: Microduck with Isaac Lab 3.0 nvidia • 20 days ago • 28
FLUX 3 Action Collection Open weights 7B world action model: base and shared encoders, SO-101 and DROID policies. Code: https://github.com/black-forest-labs/flux-action • 3 items • Updated Oct 2 • 47
view article Article Announcing SimReady Central: An Open Library of Simulation-Ready 3D Assets for Robotics and AI Factories nvidia • 20 days ago • 65
Flora Collection Flora: An Open Model Suite for Scaling Robotics Data Engines • 3 items • Updated 21 days ago • 48
OpenUSD Datasets Collection OpenUSD datasets that the Hub USD viewer renders • 12 items • Updated 21 days ago • 11
Beam 1.0 Collection Reflection’s first open-weight model, built for coding, reasoning, and agentic tasks • 4 items • Updated 25 days ago • 52
Muse Spark Open Collection Muse Spark Open model. A 816B parameter model with 42B Active parameters. BF16 and NVFP4 Weights. • 2 items • Updated 26 days ago • 177