FlowBender: Feedback-Aware Training for Self-Correcting Conditional Flows
Paper • 2606.20404 • Published • 22
diffusion models
-
-
BrainG3N: A Dual-Purpose Tokenizer for Controllable 3D Brain MRI Generation
Paper • 2606.19651 • Published • 11 -
HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining
Paper • 2606.20521 • Published • 15 -
ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation
Paper • 2607.08741 • Published • 13 -
Generative Modeling via Drifting
Paper • 2602.04770 • Published • 10