The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

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…

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

PyTorch code and models for the DINOv2 self-supervised learning method.

Code release for NeRF (Neural Radiance Fields)

CoTracker is a model for tracking any point (pixel) on a video.

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

Benchmarking Knowledge Transfer in Lifelong Robot Learning

Evaluating and reproducing real-world robot manipulation policies (e.g., RT-1, RT-1-X, Octo) in simulation under common setups (e.g., Google Robot, WidowX+Bridge) (CoRL 2024)

Official Code for RVT-2 and RVT

Experiment on combining CLIP with SAM to do open-vocabulary image segmentation.

Suite of human-collected datasets and a multi-task continuous control benchmark for open vocabulary visuolinguomotor learning.

Annotated Flow Matching paper

Dino V2 for Classification, PCA Visualization, Instance Retrival: https://arxiv.org/abs/2304.07193

Reinforcement Learning Experiments using PyBullet

Official implementation of "Towards Generalizable Vision-Language Robotic Manipulation: A Benchmark and LLM-guided 3D Policy."

Benchmarking Repository for robosuite + SAC

[NeurIPS 2024] PIVOT-R: Primitive-Driven Waypoint-Aware World Model for Robotic Manipulation

Contains implementation of AdVIL, AdRIL, and DAeQuIL algorithms from the ICML '21 Paper Of Moments and Matching.