EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL Paper • 2611.06518 • Published 14 days ago • 25
FLUX 3 Action Collection Open weights 7B world action model: base and shared encoders, SO-101 and DROID policies. Code: https://github.com/black-forest-labs/flux-action • 3 items • Updated Oct 2 • 47
Think Before You Score: Thinking Reward Model for Visual Generation Paper • 2609.37372 • Published Sep 29 • 58
WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory Paper • 2609.24984 • Published Sep 21 • 144
WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory Paper • 2609.24984 • Published Sep 21 • 144
SenseNova-U1.5: Towards Native Unified Visual Intelligence Paper • 2609.11929 • Published Sep 10 • 139
UniWorld-Design: From Pixel Generation to Layer-Native Design Paper • 2608.03971 • Published Aug 4 • 13
Alaya-EVOKE: From Linear-Scaling Supervision to Endless World Paper • 2608.13546 • Published Aug 13 • 74
UniWorld-Design: From Pixel Generation to Layer-Native Design Paper • 2608.03971 • Published Aug 4 • 13