Yunpeng

Bagel. Open-source unified multimodal model

giga-world-policy. GigaWorld-Policy: An Efficient Action-Centered World–Action Model

Embodied-AI-Guide. [Lumina具身智能社区] 具身智能技术指南 Embodied-AI-Guide

spirit-v1.5. Spirit-v1.5: A Robotic Foundation Model by Spirit AI

ESAM. [ICLR 2025, Oral] EmbodiedSAM: Online Segment Any 3D Thing in Real Time

ControlNet. Let us control diffusion models!

vggt. [CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

UniVLA. [RSS 2025] Learning to Act Anywhere with Task-centric Latent Actions

AgiBot-World. [IROS 2025 Best Paper Award Finalist & IEEE TRO 2026] The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems

Depth-Anything-V2. [NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

openpi. Python

IsaacLab. Unified framework for robot learning built on NVIDIA Isaac Sim

Qwen3. Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

cosmos-reason1. Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long chain-of-thought reasoning processes.

cosmos-predict1. Cosmos-Predict1 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.

RoboticsDiffusionTransformer. RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation

Isaac-GR00T. NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.

OpenManus. No fortress, purely open ground. OpenManus is Coming.

langchain. The agent engineering platform.

Qwen3-VL. Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

FlashMLA. FlashMLA: Efficient Multi-head Latent Attention Kernels

HE-Drive. HE-Drive: Human-Like End-to-End Driving with Vision Language Models

OpenEMMA. OpenEMMA, a permissively licensed open source "reproduction" of Waymo’s EMMA model.

DriveRecon. Python

GPD. GPD-1: Generative Pre-training for Driving

Stag. [ICCV 2025] Stag-1: Towards Realistic 4D Driving Simulation with Video Generation Model

tushare. TuShare is a utility for crawling historical data of China stocks

IC-Light. More relighting!

LGM. [ECCV 2024 Oral] LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation.

OpenCLAY. CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets

SparseDrive. SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation

Vista. [NeurIPS 2024] A Generalizable World Model for Autonomous Driving

rerun. Visualize, query, and stream to train on multimodal robotics data.

neuro-ncap. NeuroNCAP benchmark for end-to-end autonomous driving

Scale-BEV. Python

awesome-3D-gaussian-splatting. Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.

generative-ai-for-beginners. 21 Lessons, Get Started Building with Generative AI

DriveAGI. [CVPR 2024 Highlight] GenAD: Generalized Predictive Model for Autonomous Driving

DriveEnvNeRF. [ICRA 2024 Workshop] DriveEnv-NeRF: Exploration of A NeRF-Based Autonomous Driving Environment for Real-World Performance Validation

GPT4Affectivity. GPT as Psychologist? Preliminary Evaluations for GPT-4V on Visual Affective Computing

accelerate. 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

MGM. Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"

ChatSim. [CVPR2024 Highlight] Editable Scene Simulation for Autonomous Driving via LLM-Agent Collaboration

TEASER-plusplus. A fast and robust point cloud registration library

PointSAM-for-MixSup. [ICLR 2024] MixSup: Mixed-grained Supervision for Label-efficient LiDAR-based 3D Object Detection

pixel-perfect-sfm. Pixel-Perfect Structure-from-Motion with Featuremetric Refinement (ICCV 2021, Best Student Paper Award)

Forge_VFM4AD. A comprehensive survey of forging vision foundation models for autonomous driving, including challenges, methodologies, and opportunities.

Generalizable-BEV. Python

RoMe. Python

textgen. Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private.

OccWorld. [ECCV 2024] 3D World Model for Autonomous Driving

Lidar_AI_Solution. A project demonstrating Lidar related AI solutions, including three GPU accelerated Lidar/camera DL networks (PointPillars, CenterPoint, BEVFusion) and the related libs (cuPCL, 3D SparseConvolution, YUV2RGB, cuOSD,).

SelfOcc. [CVPR 2024] SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction

EmerNeRF. PyTorch Implementation of EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision

imap. High-resolution map (OpenDrive\Apollo) visualization and conversion tools

Awesome-Multimodal-Large-Language-Models. :sparkles::sparkles:Latest Advances on Multimodal Large Language Models

waymax. A JAX-based simulator for autonomous driving research.

planTF. [ICRA'2024] Rethinking Imitation-based Planner for Autonomous Driving

ADAPT. This repository is an official implementation of ADAPT: Action-aware Driving Caption Transformer, accepted by ICRA 2023.

llama. Inference code for Llama models

CausalHTP. The official PyTorch code implementation of "Human Trajectory Prediction via Counterfactual Analysis" in ICCV 2021.

DriveDreamer. [ECCV 2024] DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving

scenarionet. ScenarioNet: Scalable Traffic Scenario Management System for Autonomous Driving

InsMapper. [ECCV 2024] InsMapper: Exploring Inner-instance Information for Vectorized HD Mapping

VMA. A general map auto annotation framework based on MapTR, with high flexibility in terms of spatial scale and element type

TAP. [ICCV 2023] Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models

neuralsim. neuralsim: 3D surface reconstruction and simulation based on 3D neural rendering.

AD-MLP. Python

End-to-end-Autonomous-Driving. [IEEE T-PAMI 2024] All you need for End-to-end Autonomous Driving

onnx-modifier. A tool to modify ONNX models in a visualization fashion, based on Netron and Flask.

DFML. Official implementation of Deep Factorized Metric Learning.

VisualGLM-6B. Chinese and English multimodal conversational language model | 多模态中英双语对话语言模型

Make-A-Protagonist. Make-A-Protagonist: Generic Video Editing with An Ensemble of Experts

SurroundOcc. [ICCV 2023] SurroundOcc: Multi-camera 3D Occupancy Prediction for Autonomous Driving

OccFormer. [ICCV 2023] OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction

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.

flex-dm. [CVPR 2023 highlight] Towards Flexible Multi-modal Document Models

4d-occ-forecasting. CVPR 2023: Official code for `Point Cloud Forecasting as a Proxy for 4D Occupancy Forecasting'

OpenOccupancy. [ICCV 2023] OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception

OccDepth. Maybe the first academic open work on stereo 3D SSC method with vision-only input.

occupancy-for-nuscenes. 3D occupancy

CVPR2023-3D-Occupancy-Prediction. CVPR2023-Occupancy-Prediction-Challenge

ASAP. [CVPR 2023] Are We Ready for Vision-Centric Driving Streaming Perception? The ASAP Benchmark

TPVFormer. [CVPR 2023] An academic alternative to Tesla's occupancy network for autonomous driving.

OPERA. Official implementation of "OPERA: Omni-Supervised Representation Learning with Hierarchical Supervisions"

OpenCC. Automatic driving long tail / corner cases scenarios dataset (Anomaly detection)

pylot. Modular autonomous driving platform running on the CARLA simulator and real-world vehicles.

SOLOFusion. Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection

synthehicle. [WACVW 2023] A massive synthetic dataset for 3D multi-target multi-camera tracking and segmentation.

Learning-Deep-Learning. Paper reading notes on Deep Learning and Machine Learning

MapTR. [ICLR'23 Spotlight & ECCV'24 & IJCV'24] MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction

IDML. [TPAMI 2023] Official implementation of Introspective Deep Metric Learning.

standard-readme. A standard style for README files

DeepInteraction. [NeurIPS 2022 & TPAMI 2025] DeepInteraction: 3D Object Detection via Modality Interaction

MulimgViewer. MulimgViewer is a multi-image viewer that can open multiple images in one interface, which is convenient for image comparison and image stitching.

DEVIANT. [ECCV 2022] Official PyTorch Code of DEVIANT: Depth Equivariant Network for Monocular 3D Object Detection

omni3d. Code release for "Omni3D A Large Benchmark and Model for 3D Object Detection in the Wild"

BEVerse. The official repository for BEVerse

SurroundDepth. [CoRL 2022] SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation

HDMapNet. Python

BEVDet. Code base of the BEVDet series .

MonoScene. [CVPR 2022] "MonoScene: Monocular 3D Semantic Scene Completion": 3D Semantic Occupancy Prediction from a single image

SAFNet. [IROS 2021] Implementation of "Similarity-Aware Fusion Network for 3D Semantic Segmentation"

object-detection-usages. The brief implementation and using examples of object detection usages like, IoU, NMS, soft-NMS, SmoothL1、IoU loss、GIoU loss、 DIoU loss、CIoU loss, cross-entropy、focal-loss、GHM, AP/MAP and so on by Pytorch.

MonoFlex. Released code for Objects are Different: Flexible Monocular 3D Object Detection, CVPR21

leetcode. LeetCode Solutions: A Record of My Problem Solving Journey.( leetcode题解，记录自己的leetcode解题之路。)

CaDDN. Categorical Depth Distribution Network for Monocular 3D Object Detection (CVPR 2021 Oral)