Running Featured 84 QED-Nano: Teaching a Tiny Model to Prove Hard Theorems 📝 84 Who needs 1T parameters? Olympiad proofs with a 4B model
NVIDIA OmniDreams Collection NVIDIA OmniDreams model checkpoints and sample datasets. • 3 items • Updated 17 days ago • 10
view article Article Ulysses Sequence Parallelism: Training with Million-Token Contexts kashif, stas • Mar 9 • 33
view article Article NVIDIA Cosmos-H-Dreams: Bringing Real-Time Generative Simulation to Surgical Robotics nvidia • Jul 27 • 77
Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better Paper • 2505.23705 • Published May 29, 2025 • 1