PRISM: A Unified Framework for Photorealistic Reconstruction and Intrinsic Scene Modeling Paper • 2504.14219 • Published Apr 19, 2025 • 2
Nemotron-Terminal Collection We are releasing Nemotron-Terminal models and training datasets. • 5 items • Updated about 20 hours ago • 31
VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference Paper • 2512.01031 • Published Nov 30, 2025 • 26
Unified Latents (UL): How to train your latents Paper • 2602.17270 • Published about 1 month ago • 58
GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning Paper • 2602.12099 • Published Feb 12 • 60