Yong-Lu Li

HAT-4D-Lifting-Monocular-Video-for-4D-Multi-Object-Interactions-via-Human-Agent-Collaboration. Lifting Monocular Video for 4D Multi-Object Interactions via Human-Agent Collaboration

GR00T-WholeBodyControl. Welcome to GR00T Whole-Body Control (WBC)! This is a unified platform for developing and deploying advanced humanoid controllers. This includes: Decoupled WBC models used in NVIDIA Isaac-Gr00t, Gr00t N1.5 and N1.6 and GEAR-SONIC

ChronoFlow-Policy. Official implementation of ChronoFlow-Policy: a diffusion-based visuomotor policy that jointly models past-current-future object-gripper interaction flows for robot manipulation.

Wh0. Wh0: Generative World Models as Scalable Sources of Egocentric Human Hand Manipulation Data

Geometric_Primary_Structure. Code for CVPR2026 Paper "Revisiting Articulated Parts Perception in Robot Manipulation"

expo-ft. Python

Open-d4rt. Python

ViFailback. [CVPR 2026] Official repository for the paper "Diagnose, Correct, and Learn from Manipulation Failures via Visual Symbols".

OmniXtreme. Python

lenny-skills. 86 product management skills from Lenny's Podcast for Claude Code and AI agents. Hiring, user research, strategy, shipping, and more.

GM-X. Official Repo of The Great March Project. https://www.rhos.ai/research/gm-100

lingbot-vla. A Pragmatic VLA Foundation Model

IPR-1. Official Repo of IPR-1 Project. https://www.rhos.ai/research/ipr-1

garmagenet-impl. Official implementation for GarmageNet: A Multimodal Generative Framework for Sewing Pattern Design and Generic Garment Modeling (SIGGRAPH Asia 2025)

4dhoi_autorecon. Python

RHOS. RHOS Lab

open4dhoi_code. Python

exUMI. exUMI (CoRL 2025)

RoboHiMan. RoboHiMan: A Hierarchical Evaluation Paradigm for Compositional Generalization in Long-Horizon Manipulation

ORoboSoul.

MBA. [RA-L 2025 & ICRA 2026] :kissing_cat: Motion Before Action: Diffusing Object Motion as Manipulation Condition

SIME. [IROS 2025] SIME: Enhancing Policy Self-Improvement with Modal-level Exploration

SmartPlay. SmartPlay is a benchmark for Large Language Models (LLMs). Uses a variety of games to test various important LLM capabilities as agents. SmartPlay is designed to be easy to use, and to support future development of LLMs.

TactAR_APP. [RSS 2025] TactAR teleopeartion APP in "Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation"

reactive_diffusion_policy. [RSS 2025] Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation

Awesome-Embodied-AI-Job. Lumina Robotics Talent Call | Lumina社区具身智能招贤榜 | A list for Embodied AI / Robotics Jobs (PhD, RA, intern, etc

open-3dhoi. Python

DensePolicy2D. [ICCV 2025] :bouquet: 2D version of Dense Policy (DSP)

DensePolicy. [ICCV 2025] :bouquet: Dense Policy (DSP): Bidirectional Autoregressive Learning of Actions

M3VOS_Experiment. Jupyter Notebook

SemiAuto-Multi-Level-Annotation-Tool. This repo is the office implement of a Semi-Auto Multi-Level Annotation Tool used in M-cube-VOS. It allows for user to annotate the mask of target objects efficiently.

mujoco_playground. An open-source library for GPU-accelerated robot learning and sim-to-real transfer.

NSFC-LaTex. BibTeX Style

openpi. Python

cosmos. NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.

Open-Sora-Plan. This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

Open-Sora. Open-Sora: Democratizing Efficient Video Production for All

Awesome-Human-Motion. An aggregation of human motion understanding research.

VidTok. a family of versatile and state-of-the-art video tokenizers.

diamond. DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.

GenieRedux. A framework for training world models with virtual environments, complete with annotated environment dataset (RetroAct), exploration agent (AutoExplore Agent), and GenieRedux-G - an implementation of Genie with enhancements

ADAM. We introduce ADAM, An emboDied causal Agent in Minecraft, that can autonomously navigate the open world, perceive multimodal contexts, learn causal world knowledge, and tackle complex tasks through lifelong learning.

Playable-Game-Generation. An open-source lightweight game generation paradigm. It includes everything from data processing to model architecture design and playability-based evaluation methods. The game runs at 20 FPS on a single consumer-grade graphics card (RTX-2060) while maintaining high playability.

HunyuanVideo. HunyuanVideo: A Systematic Framework For Large Video Generation Model

VisionZip. Official repository for VisionZip (CVPR 2025)

HDyS. Homogeneous Dynamics Space for Heterogeneous Humans (CVPR 2025)

ImDy. ImDy: Human Inverse Dynamics from Imitated Observations (ICLR 2025)

LLM_Inception. [ICLR 2025] This repo is the official implementation of "The Labyrinth of Links: Navigating the Associative Maze of Multi-modal LLMs".

TwoStageReason. Official implementation of ECCV 2024 paper: Take A Step Back: Rethinking the Two Stages in Visual Reasoning

lerobot. 🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

Motion-Occupancy-Base. Official repository for gathering data of Revisit Human-Scene Interaction via Space Occupancy (ECCV 2024).

HumanVLA. Python

nsfc. nsfc - 国家自然科学基金项目LaTeX模版(面地青CBA)

Symbol-LLM. Code for NeurIPS2023 Paper "Symbol-LLM: Leverage Language Models for Symbolic System in Visual Human Activity Reasoning"

LoRS_Distill. Code for our ICML'24 on multimodal dataset distillation

EgoPCA. This is official code of ICCV'23 paper: EgoPCA: A New Framework for Egocentric Hand-Object Interaction Understanding.

video_distillation. Official implementation of Dancing with Still Images: Video Distillation via Static-Dynamic Disentanglement.

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

InternLM-XComposer. InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions

MultiPLY. Code for MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World

myosuite. MyoSuite is a collection of environments/tasks to be solved by musculoskeletal models simulated with the MuJoCo physics engine and wrapped in the OpenAI gym API.

search_with_lepton. Building a quick conversation-based search demo with Lepton AI.

Wonder3D. Single Image to 3D using Cross-Domain Diffusion for 3D Generation

octo. Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.

ObjectConceptLearning. This the official repository of OCL (ICCV 2023).

GoldFromOres-BiLP. Preview code of ECCV'24 paper "Distill Gold from Massive Ores" (BiLP)

awesome-video-self-supervised-learning. A curated list of awesome self-supervised learning methods in videos

DiffHOI. Official implementation of the paper "Boosting Human-Object Interaction Detection with Text-to-Image Diffusion Model"

Pose_to_SMPL. A tool to fit SMPL parameters from 3D-pose datasets that contain key-points of human body.

Total-Recon. [ICCV 2023] Total-Recon: Deformable Scene Reconstruction for Embodied View Synthesis

taichi. Productive, portable, and performant GPU programming in Python.

lerf. Code for LERF: Language Embedded Radiance Fields

Anything-3D. Segment-Anything + 3D. Let's lift anything to 3D.

stable-dreamfusion. Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

taichi-nerfs. Implementations of NeRF variants based on Taichi + PyTorch

Segment-Everything-Everywhere-All-At-Once. [NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

EditAnything. Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc. (ACM MM)

segment-anything. 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.

VL-CheckList. Evaluating Vision & Language Pretraining Models with Objects, Attributes and Relations. [EMNLP 2022]

open_flamingo. An open-source framework for training large multimodal models.

LLM-in-Vision. Recent LLM-based CV and related works. Welcome to comment/contribute!

AlphaTracker. AlphaTracker is a computer vision pipeline with the practical and real-time advantages , which requires minimal hardware requirements and produces reliable tracking of multiple unmarked animals. An easy-to-use user interface further enables manual inspection and curation of results.

Transformer-in-Vision. Recent Transformer-based CV and related works.

DINO. [ICLR 2023] Official implementation of the paper "DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection"

detrex. detrex is a research platform for DETR-based object detection, segmentation, pose estimation and other visual recognition tasks.

mvig-rhos.github.io. HTML

Robotics-Conference-Acceptance-Rate. Statistics of acceptance rate for the main robotics conference

DnD. Code for "D&D: Learning Human Dynamics from Dynamic Camera", ECCV 2022 Oral

aitviewer. A set of tools to visualize and interact with sequences of 3D data.

unity-antagonistic-controller. Generating Upper-Body Motion for Real-Time Characters Making their Way through Dynamic Environments - 2022 - SCA

YLearn. YLearn, a pun of "learn why", is a python package for causal inference

GAP. official implementation for Language Supervised Training for Skeleton-based Action Recognition

Sandwich. Bidirectional Mapping between Action Physical-Semantic Space

alpa. Training and serving large-scale neural networks with auto parallelization.

academia-hugo. Academia is a Hugo resume theme. You can showcase your academic resume, publications and talks using this theme.

Awesome-Dataset-Distillation. A curated list of awesome papers on dataset distillation and related applications.

GLAMR. [CVPR 2022 Oral] Official PyTorch Implementation of "GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras”.

Partial_Distance_Correlation. This is the official GitHub for paper: On the Versatile Uses of Partial Distance Correlation in Deep Learning, in ECCV 2022

ROMP. Monocular, One-stage, Regression of Multiple 3D People and their 3D positions & trajectories in camera & global coordinates. ROMP[ICCV21], BEV[CVPR22], TRACE[CVPR2023]

DLSA. The code accompanying our ECCV'22 papers: Constructing Balance from Imbalance for Long-tailed Image Recognition

Body-Part-Map-for-Interactiveness. Code for ECCV2022 Paper "Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detection"

parti.

Interactiveness-Field. Python

ZeroVL. [ECCV2022] Contrastive Vision-Language Pre-training with Limited Resources

DCR. Official implementation of our CVPR'22 paper.

open_clip. An open source implementation of CLIP.

mtt-distillation. Official code for our CVPR '22 paper "Dataset Distillation by Matching Training Trajectories"

CPPF. CPPF: Towards Robust Category-Level 9D Pose Estimation in the Wild (CVPR2022)

OC-Immunity. Python

HAKE-AVA. Shell

sampling-argmax. Code for "Localization with Sampling-Argmax", NeurIPS 2021

ICON. [CVPR'22] ICON: Implicit Clothed humans Obtained from Normals

awesome-3dbody-papers. 😎Awesome list of papers about 3D body

sampling-argmax. Code for "Localization with Sampling-Argmax", NeurIPS 2021

pysot. SenseTime Research platform for single object tracking, implementing algorithms like SiamRPN and SiamMask.

hellosiyuan. Python

awesome-long-tail-learning.

model-vs-human. Benchmark your model on out-of-distribution datasets with carefully collected human comparison data (NeurIPS 2021 Oral)

AI4Animation. Bringing Characters to Life with Computer Brains in Unity

hotr. Official repository for HOTR: End-to-End Human-Object Interaction Detection with Transformers (CVPR'21, Oral Presentation)

SlowFast. PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

ConsNet. 🚴‍♂️ ConsNet: Learning Consistency Graph for Zero-Shot Human-Object Interaction Detection (MM 2020)

ahp. AHP: Amodal Human Perception dataset

PGT. Official code of paper "PGT: A Progressive Method for Training Models on Long Videos" on CVPR2021

awesome-holistic-3d. A list of papers and resources (data,code,etc) for holistic 3D reconstruction in computer vision

Handeye-Calibration-ROS. 🤖 Elaborated hand-eye calibration tutorials (ROS-binding)

MySummary. My Design Philosophy Summary (Most of them are in Chinese)

CLIP. CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

github-buttons. Showcase the success of any GitHub repo or user with these simple, static buttons with dynamic counts.

CanonicalVoting. Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes (CVPR2022)

UKPGAN. UKPGAN: A General Self-Supervised Keypoint Detector (CVPR2022)

OneNet. [ICML2021] What Makes for End-to-End Object Detection

SJTUThesis. 上海交通大学 LaTeX 论文模板 | Shanghai Jiao Tong University LaTeX Thesis Template

HAKE-Action-Torch. HAKE-Action in PyTorch

object_level_visual_reasoning. Pytorch Implementation of "Object level Visual Reasoning in Videos", F. Baradel, N. Neverova, C. Wolf, J. Mille, G. Mori , ECCV 2018

Halpe-FullBody. Halpe: full body human pose estimation and human-object interaction detection dataset

human_body_prior. VPoser: Variational Human Pose Prior

zero_shot_hoi. Discovering human interaction with novel objects via zero-shot learning, CVPR, 2020

AlphAction. Spatio-Temporal Action Localization System

taskmodularnets. A set of neural network modules, which are small fully connected layers operating in semantic concept space. These modules are configured through a gating function conditioned on the task to produce features representing the compatibility between the input image and the concept under consideration.

HOI-Learning-List. A list of Human-Object Interaction Learning.

SymNet. As a part of the HAKE project (HAKE-Object), code for SymNet (CVPR'20 and TPAMI'21).

DJ-RN. As a part of HAKE project (HAKE-3D). Code for our CVPR2020 paper "Detailed 2D-3D Joint Representation for Human-Object Interaction".

HAKE-Action. As a part of the HAKE project, includes the reproduced SOTA models and the corresponding HAKE-enhanced versions (CVPR2020).

Few-Shot-Object-Detection-Dataset.

attributes-as-operators. Attribute-Object Visual Composition using Attributes as Operators

furniture. IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Tasks

awesome-point-cloud-analysis. A list of papers and datasets about point cloud analysis (processing)

smplify-x. Expressive Body Capture: 3D Hands, Face, and Body from a Single Image

Instaboost. Code for ICCV2019 paper "InstaBoost: Boosting Instance Segmentation Via Probability Map Guided Copy-Pasting"

HAKE. HAKE: Human Activity Knowledge Engine (CVPR'18/19/20, NeurIPS'20, TPAMI'21)

labelKeypoint. Keypoints label tools

BBox-Label-Tool. A simple tool for labeling object bounding boxes in images

AlphaPose. Multi-Person Pose Estimation System

Mask_RCNN. Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow(tf1.3.0+cuda8+cudnn6)

video-long-term-feature-banks. Long-Term Feature Banks for Detailed Video Understanding

SRDA-ECCV2018. ECCV2018: SRDA: Generating Instance Segmentation Annotation via Scanning, Reasoning and Domain Adaptation

Transferable-Interactiveness-Network. Code for Transferable Interactiveness Knowledge for Human-Object Interaction Detection. (CVPR'19, TPAMI'21)

GAN_Theories. Resources and Implementations of Generative Adversarial Nets which are focusing on how to stabilize training process and generate high quality images: DCGAN, WGAN, EBGAN, BEGAN, etc.

iCAN. [BMVC 2018] iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection

PRIN. Pointwise Rotation-Invariant Network (AAAI 2020)

PRNet. Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network (ECCV 2018)

jsonlab. JSONLab: compact, portable, robust JSON/binary-JSON encoder/decoder for MATLAB/Octave

labelKeypoint. Keypoints label tools

bundler_sfm. Bundler Structure from Motion Toolkit

ai-deadlines. :alarm_clock: AI conference deadline countdowns

AlphaPose. Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System

the-gan-zoo. A list of all named GANs!

co-fusion. Co-Fusion: Real-time Segmentation, Tracking and Fusion of Multiple Objects

MNC. Instance-aware Semantic Segmentation via Multi-task Network Cascades

openMVS. open Multi-View Stereo reconstruction library

vaeblog.

fast-neural-style. Feedforward style transfer

PhotographicImageSynthesis. Photographic Image Synthesis with Cascaded Refinement Networks

opencv. Open Source Computer Vision Library

caffe. Caffe: a fast open framework for deep learning.