Yurong You

flashdrive. Flash Vision-Language-Action Inference for Autonomous Driving

alpagym. AlpaGym is a reinforcement-learning framework for end-to-end autonomous-driving policies.

alpamayo-recipes. Developer Hub for NVIDIA Alpamayo, containing ready-to-use recipes for fine-tuning, reinforcement-learning post-training, quantization, and deployment.

alpamayo-autoware. Python

alpamayo1.5. NVIDIA Alpamayo 1.5 Nano is an open 10B reasoning VLA model for autonomous vehicles with reinforcement-learning enhanced reasoning, navigation guidance, and visual question answering.

DroPE. Extending the Context of Pretrained LLMs by Dropping Their Positional Embedding

alpamayo. NVIDIA Alpamayo 1 Nano is an open 10B reasoning VLA model for autonomous vehicles that pairs driving trajectories with Chain-of-Causation reasoning.

alpasim. AlpaSim is an open-source autonomous vehicle simulation platform designed for development and testing of end-to-end AV policies

physical_ai_av. Devkit and documentation for the NVIDIA Physical AI Autonomous Vehicles Dataset

flow_matching. A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

cosmos-rl. Cosmos-RL is a flexible and scalable Reinforcement Learning framework specialized for Physical AI applications.

Megatron-Energon. Megatron's multi-modal data loader

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.

build-nanogpt. Video+code lecture on building nanoGPT from scratch

3DGM. Official PyTorch implementation of 3D Gaussian Mapping (3DGM)

neurad-studio. [CVPR2024] NeuRAD: Neural Rendering for Autonomous Driving

pypose. A library for differentiable robotics on manifolds.

instant-nsr-pl. Neural Surface reconstruction based on Instant-NGP. Efficient and customizable boilerplate for your research projects. Train NeuS in 10min!

gemma_pytorch. The official PyTorch implementation of Google's Gemma models

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

tiny-cuda-nn. Lightning fast C++/CUDA neural network framework

ngp_pl. Instant-ngp in pytorch+cuda trained with pytorch-lightning (high quality with high speed, with only few lines of legible code)

nerf_pl. NeRF (Neural Radiance Fields) and NeRF in the Wild using pytorch-lightning

kiss-icp. A LiDAR odometry pipeline that just works

openinterpreter. A coding agent for open models like Kimi K3

llama2.c. Inference Llama 2 in one file of pure C

dift. [NeurIPS'23] Emergent Correspondence from Image Diffusion

smoothquant. [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

Speaker-Recognition-Demo. A ResNet Speaker Recognition&Verification Demo

Variational-GP-Decoupled-Conditionals. Variational GP with decoupled conditionals

BTG. AGS Script

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.

VirTex_replication. Python

bitsandbytes. Accessible large language models via k-bit quantization for PyTorch.

ManiSkill-Legacy. SAPIEN Manipulation Skill Benchmark (NeurIPS 2021 Track on Datasets and Benchmarks)

chatgpt-google-extension. This project is deprecated. Check my new project ChatHub:

AMPL_NeurIPS2022. Python

skypilot. The AI Compute Platform for frontier teams. SkyPilot turns fragmented AI compute into one AI supercomputer, so frontier AI teams build custom intelligence faster.

Easy-GPU-PV. A Project dedicated to making GPU Partitioning on Windows easier!

mmcv. OpenMMLab Computer Vision Foundation

ultimatevocalremovergui. GUI for a Vocal Remover that uses Deep Neural Networks.

vista. Data-driven simulation for training and evaluating full-scale autonomous vehicles.

bevfusion. [ICRA'23] BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation

open-gpu-kernel-modules. NVIDIA Linux open GPU kernel module source

STARTUP. Python

StayPositive. Jupyter Notebook

lang-seg. Language-Driven Semantic Segmentation

pseudolidar-tree-detection. Python

FNNS. Jupyter Notebook

ConvNeXt. Code release for ConvNeXt model

spconv. Spatial Sparse Convolution Library

BetterDisplay. Unlock your displays on your Mac! Flexible HiDPI scaling, XDR/HDR extra brightness, virtual screens, DDC control, extra dimming, PIP/streaming, EDID override and lots more!

point_labeler. My awesome point cloud labeling tool

Compiler-Design-Implementation. C++

Modern-CPP-Programming. Modern C++ Programming Course (C++03/11/14/17/20/23/26)

lietorch. Cuda

faiss. A library for efficient similarity search and clustering of dense vectors.

kmcuda. Large scale K-means and K-nn implementation on NVIDIA GPU / CUDA

ShapeTextureDebiasedTraining. Code and models for the paper Shape-Texture Debiased Neural Network Training (ICLR 2021)

VirtualTeaching. DIY setup for virtual teaching on ubuntu

kitti360Scripts. This repository contains utility scripts for the KITTI-360 dataset.

OpenPCDet. OpenPCDet Toolbox for LiDAR-based 3D Object Detection.

DSGN. [CVPR 2020] DSGN: Deep Stereo Geometry Network for 3D Object Detection

nerf. Code release for NeRF (Neural Radiance Fields)

PointFlowRenderer. Code for rendering the point cloud figures in paper: "PointFlow : 3D Point Cloud Generation with Continuous Normalizing Flows"

MoEx. MoEx (Moment Exchange)

UnblockNeteaseMusic. Revive unavailable songs for Netease Cloud Music

Pseudo_Lidar_V2. (ICLR) Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving

PointRCNN. PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud, CVPR 2019.

detectron2. Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

pytorch3d. PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

Positional-Normalization. Positional Normalization (PONO) and Moment Shortcut (MS)

DeepPruner. DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch (ICCV 2019)

simple_shot. Python

torchdiffeq. Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.

jax. Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

nuscenes-devkit. The devkit of the nuScenes dataset.

botorch. Bayesian optimization in PyTorch

argoverse-api. Official GitHub repository for Argoverse dataset

mixup-cifar10. mixup: Beyond Empirical Risk Minimization

LDLS. LDLS (Label Diffusion LiDAR Segmentation) algorithm for instance segmentation of LiDAR point clouds.

waymo-open-dataset. Waymo Open Dataset

BayesianOptimization. A Python implementation of global optimization with gaussian processes.

github-do-not-ban-us. GitHub do not ban us from open source world :iran:

gdrive. Google Drive CLI Client

pyamgx. GPU accelerated multigrid library for Python

cuda-samples. Samples for CUDA Developers which demonstrates features in CUDA Toolkit

deeplearning-models. A collection of various deep learning architectures, models, and tips

or-tools. Google's Operations Research tools:

pykdtree. Fast kd-tree implementation in Python

segtree-transformer-v0. Code for SegTree Transformer (ICLR-RLGM 2019).

simple-blackbox-attack. Code for ICML 2019 paper "Simple Black-box Adversarial Attacks"

SGC. official implementation for the paper "Simplifying Graph Convolutional Networks"

bert_score. BERT score for text generation

amc-models. [ECCV 2018] AMC: AutoML for Model Compression and Acceleration on Mobile Devices

lsyncd. Lsyncd (Live Syncing Daemon) synchronizes local directories with remote targets

fairseq. Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

pseudo_lidar. (CVPR 2019) Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving

AnyNet. (ICRA) Anytime Stereo Image Depth Estimation on Mobile Devices

xgboost. Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow

google-drive-ocamlfuse. FUSE filesystem over Google Drive

DARENet. (CVPR) Resource Aware Person Re-identification across Multiple Resolutions

audio_adversarial_examples. Targeted Adversarial Examples on Speech-to-Text systems

deepspeech.pytorch. Speech Recognition using DeepSpeech2.

sjtu-summer2018. Course material for "Numerical Methods for Data Science" (SJTU, summer 2018)

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

gpytorch. A highly efficient implementation of Gaussian Processes in PyTorch

Cheat-Sheets.

deep-image-prior. Image restoration with neural networks but without learning.

SQLNet. Neural Network for generating structured queries from natural language.

MSDNet. Multi-Scale Dense Networks for Resource Efficient Image Classification （ICLR 2018 Oral）

triplet-reid. Code for reproducing the results of our "In Defense of the Triplet Loss for Person Re-Identification" paper.

perls. SteamVR - BulletPhysics - ROS interface

language-grounding-experiments. To do experiments on language grounding.

tensorflow-rl. Implementations of deep RL papers and random experimentation

tensorpack. A Neural Net Training Interface on TensorFlow, with focus on speed + flexibility

imitation. Code for the paper "Generative Adversarial Imitation Learning"

pysc2. StarCraft II Learning Environment

baselines. OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

trimesh. Python library for loading and using triangular meshes.

tensorforce. Tensorforce: a TensorFlow library for applied reinforcement learning

mastering_ros. This repository contains exercise files of the book "Mastering ROS for Robotics Programming"

DeepRL-Agents. A set of Deep Reinforcement Learning Agents implemented in Tensorflow.

tensorflow-reinforce. Implementations of Reinforcement Learning Models in Tensorflow

DDPG. Reimplementation of DDPG(Continuous Control with Deep Reinforcement Learning) based on OpenAI Gym + Tensorflow

fairseq-lua. Facebook AI Research Sequence-to-Sequence Toolkit

TensorLayer. Deep Learning and Reinforcement Learning Library for Scientists and Engineers

nematus. Open-Source Neural Machine Translation in Tensorflow

GA3C. Hybrid CPU/GPU implementation of the A3C algorithm for deep reinforcement learning.

ray-tracing. Ray Tracing

gallifrey. Course assignment of CS230.

Deep-Reinforcement-Learning-Survey. My Exploration on Deep Reinforcement Learning Survey

awesome-rl. Reinforcement learning resources curated

suterusu. An LKM rootkit targeting Linux 2.6/3.x on x86(_64), and ARM

libhijack. Runtime Process Infection Made Easy

deep-reinforcement-learning-papers. A list of recent papers regarding deep reinforcement learning

Deep-Learning-Papers-Reading-Roadmap. Deep Learning papers reading roadmap for anyone who are eager to learn this amazing tech!

DLCourse_AS. DeepLearning Course Assignments

Atari. Persistent advantage learning dueling double DQN for the Arcade Learning Environment

MasterCompiler. A naive compiler from Mx* to MIPS

jekyll-douban-collections. Douban Plugin for Jekyll