Automatic Textbook Formalization(github.com)

27 points by tzury 6 months ago | 8 comments

VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models(github.com)

49 points by MrTrvp 2 years ago | 5 comments

Pearl: A Production-Ready Reinforcement Learning Agent(github.com)

61 points by da4id 2 years ago | 7 comments

Faiss: A library for efficient similarity search(github.com)

236 points by tosh 3 years ago | 47 comments

VGGT: Visual Geometry Grounded Transformer(github.com)

182 points by xnx 1 year ago | 40 comments

SAM 2: Segment Anything in Images and Videos(github.com)

674 points by xenova 2 years ago | 122 comments

GitHub repository from Meta's facebookresearch with inference code, model checkpoints, and example notebooks for Segment Anything Model 2 (SAM 2).