Tianyuan Yuan

lingbot-video. Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

RoboTwin. RoboTwin 2.0 Offical Repo

lingbot-va. [RSS 2026] Causal video-action world model for generalist robot control

minimal-light. A simple and elegant Jekyll theme for an academic personal homepage

any4lerobot. 🎁 A collection of utilities for LeRobot.

VITRA. [ICRA 2026] VITRA: Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos

VLMEvalKit. Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks

mast3r. Grounding Image Matching in 3D with MASt3R

dlimp. dataloading is my passion

bridge_data_v2. Python

UniDepth. Universal Monocular Metric Depth Estimation

Video-Depth-Anything. [CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

CannotMax. Python

openpi. Python

open-pi-zero. Re-implementation of pi0 vision-language-action (VLA) model from Physical Intelligence

openvla. OpenVLA: An open-source vision-language-action model for robotic manipulation.

LIBERO. Benchmarking Knowledge Transfer in Lifelong Robot Learning

mega-sam. Code for the project "MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos"

SplatFormer. [ICLR' 25] SplatFormer: Point Transformer for Robust 3D Gaussian Splatting

point_odyssey. Official code for PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking (ICCV 2023)

wild-gaussian-splatting. DUSt3R + Gaussian Splatting

depthsplat. [CVPR'25] DepthSplat: Connecting Gaussian Splatting and Depth

spann3r. [3DV'25 Award Candidate] 3D Reconstruction with Spatial Memory

monst3r. Official Implementation of paper "MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"

splatt3r. Official repository for Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs

flash3d. Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image

poly-diffuse. Code for "PolyDiffuse: Polygonal Shape Reconstruction via Guided Set Diffusion Models", NeurIPS 2023

GitHub520. :kissing_heart: 让你“爱”上 GitHub，解决访问时图裂、加载慢的问题。（无需安装）

2d-gaussian-splatting. [SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields

3DShape2VecSet. Python

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

TRIPS. C++

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

neural_map_prior. The official implementation of the CVPR2023 paper titled “Neural Map Prior for Autonomous Driving”.

Diff-Foley. Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models

nerfstudio. A collaboration friendly studio for NeRFs

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

StreamPETR. [ICCV 2023] StreamPETR: Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection

trackerslist. Updated list of public BitTorrent trackers

UNINEXT. [CVPR'23] Universal Instance Perception as Object Discovery and Retrieval

unilm. Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

argoverse-navmap. Python

OpenPerceptionX.github.io. HTML

MaaAssistantArknights. 《明日方舟》小助手，全日常一键长草！| A one-click tool for the daily tasks of Arknights, supporting all clients.

mmdetection. OpenMMLab Detection Toolbox and Benchmark

libpku. 贵校课程资料民间整理