MakeAnything: Harnessing Diffusion Transformers for Multi-Domain Procedural Sequence Generation Paper • 2502.01572 • Published 15 days ago • 20
AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Understanding Paper • 2502.01341 • Published 16 days ago • 35
COCONut-PanCap: Joint Panoptic Segmentation and Grounded Captions for Fine-Grained Understanding and Generation Paper • 2502.02589 • Published 14 days ago • 9
VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models Paper • 2502.02492 • Published 14 days ago • 55
OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models Paper • 2502.01061 • Published 16 days ago • 178