Advancing End-to-End Pixel Space Generative Modeling via Self-supervised Pre-training Paper • 2510.12586 • Published 15 days ago • 107
view article Article SAIR: Accelerating Pharma R&D with AI-Powered Structural Intelligence By SandboxAQ and 3 others • Sep 2 • 35
Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies Paper • 2508.20072 • Published Aug 27 • 30
Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels Paper • 2508.17437 • Published Aug 20 • 36
MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds Paper • 2508.14879 • Published Aug 20 • 65
Do What? Teaching Vision-Language-Action Models to Reject the Impossible Paper • 2508.16292 • Published Aug 22 • 9
NVIDIA Nemotron V2 Collection Open, Production-ready Enterprise Models. Nvidia Open Model license. • 9 items • Updated about 16 hours ago • 70
view article Article Introducing Pivotal Token Search (PTS): Targeting Critical Decision Points in LLM Training By codelion • May 17 • 10