SpatialTree: How Spatial Abilities Branch Out in MLLMs Paper โข 2512.20617 โข Published 13 days ago โข 42
Towards Scalable Pre-training of Visual Tokenizers for Generation Paper โข 2512.13687 โข Published 21 days ago โข 99
Running on Zero Featured 337 Depth Anything 3 ๐ข 337 Create detailed depth maps from images using Depth Anything 3
Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers Paper โข 2510.07316 โข Published Oct 8, 2025 โข 3