WorldSimBench: Towards Video Generation Models as World Simulators Paper • 2410.18072 • Published 15 days ago • 17
MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models Paper • 2410.13370 • Published 21 days ago • 36
Towards Synergistic, Generalized, and Efficient Dual-System for Robotic Manipulation Paper • 2410.08001 • Published 28 days ago • 4
Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis Paper • 2410.08261 • Published 28 days ago • 49