The official Meta Llama 3 GitHub site

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

[ECCV 2024] PyTorch implementation of "Real-time Holistic Robot Pose Estimation with Unknown States"

6D Object Pose Estimation using RGBD Data and Fast-ICP

Official implementation of "SUGAR: Pre-training 3D Visual Representations for Robotics" (CVPR'24).

[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention

Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone

FilterPrompt: Guiding Image Transfer in Diffusion Models

repo for NIMBLE: A Non-rigid Hand Model with Bones and Muscles

[arXiv preprint] The official code of paper "Open-Vocabulary SAM".

[ECCV 2024] 🎉 Official repository of "Robo-ABC: Affordance Generalization Beyond Categories via Semantic Correspondence for Robot Manipulation"

Official repository of "CORE4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object REarrangement".

From anything to mesh like human artists. Official impl. of "MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers"

The implementation of our CVPR 2024 paper "Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapes."

Official implementation of the RLC 2024 paper "Policy-Guided Diffusion"

VMamba: Visual State Space Models，code is based on mamba

“百聆”是一个基于LLaMA的语言对齐增强的英语/中文大语言模型，具有优越的英语/中文能力，在多语言和通用任务等多项测试中取得ChatGPT 90%的性能。BayLing is an English/Chinese LLM equipped with advanced language alignment, showing superior capability in English/Ch…

Official codebase for "Any-point Trajectory Modeling for Policy Learning"

Instruct2Act: Mapping Multi-modality Instructions to Robotic Actions with Large Language Model

Pytorch official implementation for our CVPR-2024 paper "AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning".

The repo of paper `RoboMamba: Multimodal State Space Model for Efficient Robot Reasoning and Manipulation`

Code for the paper "3D Diffuser Actor: Policy Diffusion with 3D Scene Representations"

Official repository for "AM-RADIO: Reduce All Domains Into One"

[CVPR 2024✨Highlight] Official repository for HOLD, the first method that jointly reconstructs articulated hands and objects from monocular videos without assuming a pre-scanned object template and…