zhangjb416

VQASynth

Compose multimodal datasets 🎹

mobile_manipulation_papers

Papers in Mobile Manipulation (Personal Collection)

ScanReason

[ECCV 2024] Empowering 3D Visual Grounding with Reasoning Capabilities

embodied-generalist

[ICML 2024] Official code repository for 3D embodied generalist agent LEO

OmniGibson

OmniGibson: a platform for accelerating Embodied AI research built upon NVIDIA's Omniverse engine. Join our Discord for support: https://discord.gg/bccR5vGFEx

cambrian

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

robocasa

RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots

Depth-Anything-V2

Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

MoMa-LLM

Language-Grounded Dynamic Scene Graphs for Interactive Object Search with Mobile Manipulation. Project website: http://moma-llm.cs.uni-freiburg.de

Grounded_3D-LLM

Code&Data for Grounded 3D-LLM with Referent Tokens

EmbodiedScan

[CVPR 2024] EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI

SceneTracker

SceneTracker: Long-term Scene Flow Estimation Network

Track-Anything

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

mimicgen

This code corresponds to simulation environments used as part of the MimicGen project.

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

RoboEXP

RoboEXP: Action-Conditioned Scene Graph via Interactive Exploration for Robotic Manipulation

3D-VLA

[ICML 2024] 3D-VLA: A 3D Vision-Language-Action Generative World Model

AVDC

Official repository of Learning to Act from Actionless Videos through Dense Correspondences.

ok-robot

An open, modular framework for zero-shot, language conditioned pick-and-drop tasks in arbitrary homes.

Semantic-Segment-Anything

Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).

Depth-Anything

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

LIBERO

Benchmarking Knowledge Transfer in Lifelong Robot Learning

GROOT

Official implementation of GROOT, CoRL 2023

peract

Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation

d3fields

[arXiv] D^3Fields: Dynamic 3D Descriptor Fields for Zero-Shot Generalizable Robotic Manipulation

lerftogo

arnold

[ICCV 2023] Official code repository for ARNOLD benchmark

rh20t_api

ijepa

Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive architecture."

IsaacLab

Unified framework for robot learning built on NVIDIA Isaac Sim