view article Article Unlocking Longer Generation with Key-Value Cache Quantization RaushanTurganbay • May 16, 2024 • 57
SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer Paper • 2605.15178 • Published 25 days ago • 86
Aligning Latent Geometry for Spherical Flow Matching in Image Generation Paper • 2605.15193 • Published 25 days ago • 8
nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 Any-to-Any • 33B • Updated about 1 month ago • 513k • 337