PUMA: Empowering Unified MLLM with Multi-granular Visual Generation Paper • 2410.13861 • Published Oct 17 • 53
LVD-2M: A Long-take Video Dataset with Temporally Dense Captions Paper • 2410.10816 • Published Oct 14 • 19
Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding Paper • 2410.01699 • Published Oct 2 • 18
Loong: Generating Minute-level Long Videos with Autoregressive Language Models Paper • 2410.02757 • Published Oct 3 • 36
LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness Paper • 2409.18125 • Published Sep 26 • 33
DreamWaltz-G: Expressive 3D Gaussian Avatars from Skeleton-Guided 2D Diffusion Paper • 2409.17145 • Published Sep 25 • 13
T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation Paper • 2407.14505 • Published Jul 19 • 25