SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features Paper • 2502.14786 • Published 1 day ago • 79
DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior Paper • 2310.16818 • Published Oct 25, 2023 • 32
Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling Paper • 2501.17811 • Published 23 days ago • 6
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention Paper • 2502.11089 • Published 6 days ago • 129