SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture Paper • 2605.12500 • Published 6 days ago • 172
view article Article NEO-unify: Building Native Multimodal Unified Models End to End sensenova • Mar 5 • 161
AR-Lightx2v Collection Efficient autoregressive video generation (i.e., the Self-Forcing family) checkpoints. • 2 items • Updated Mar 2 • 3
AR-Lightx2v Collection Efficient autoregressive video generation (i.e., the Self-Forcing family) checkpoints. • 2 items • Updated Mar 2 • 3
GenRL Collection Model collections trained with our framework: https://github.com/ModelTC/GenRL • 3 items • Updated Feb 11 • 3