Yin Cui

OmniShotCut. OmniShotCut is a sensitive and more informative SoTA on Shot Boundary Detection task.

learn-claude-code. Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

cosmos-reason2. Cosmos-Reason2 models understand the physical common sense and generate appropriate embodied decisions in natural language through long chain-of-thought reasoning processes.

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

sage. Official Code Release of SAGE: Scalable Agentic 3D Scene Generation for Embodied AI

Awesome-World-Models. A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.

cosmos-predict2.5. Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the future state of the world in the form of video.

physical-ai-bench. [CVPR 2026 Oral] PAI-Bench: A Comprehensive Benchmark for Physical AI

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

NFT. Implementation of Negative-aware Finetuning (NFT) algorithm for "Bridging Supervised Learning and Reinforcement Learning in Math Reasoning"

gemini-cli. An open-source AI agent that brings the power of Gemini directly into your terminal.

cosmos-predict2. Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.

cosmos-xenna. Python library for building and running distributed data pipelines using Ray

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.

DaTaSeg-Objects365-Instance-Segmentation. We release the DaTaSeg Objects365 Instance Segmentation Dataset introduced in the DaTaSeg paper, which can be used as an evaluation benchmark for weakly or semi supervised segmentation.

describe-anything. [ICCV 2025] Implementation for Describe Anything: Detailed Localized Image and Video Captioning

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. 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.

TokenBench. A Video Tokenizer Evaluation Dataset

Cosmos-Tokenizer. A suite of image and video neural tokenizers

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

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

LLM101n. LLM101n: Let's build a Storyteller

yarn. YaRN: Efficient Context Window Extension of Large Language Models

dclm. DataComp for Language Models

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

llama3. The official Meta Llama 3 GitHub site

torchtitan. A PyTorch native platform for training generative AI models

Blender-Donut-Tutorial. :doughnut: Beginner Blender 4.0 Tutorial

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

awesome-6d-object. Awesome work on object 6 DoF pose estimation

dm-haiku. JAX-based neural network library

Awesome-Transformer-Attention. An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites

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

CVinW_Readings. A collection of papers on the topic of ``Computer Vision in the Wild (CVinW)''

open_clip. An open source implementation of CLIP.

d2l-en. Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

uncertainty-baselines. High-quality implementations of standard and SOTA methods on a variety of tasks.

vision_transformer. Jupyter Notebook

Awesome-Video-Datasets. Video datasets

GSAM. PyTorch repository for ICLR 2022 paper (GSAM) which improves generalization (e.g. +3.8% top-1 accuracy on ImageNet with ViT-B/32)

jonbarron.github.io. HTML

dmvr. Python

newt. Natural World Tasks

TF_JAX_tutorials. All about the fundamental blocks of TF and JAX!

Awesome-Knowledge-Distillation. Awesome Knowledge-Distillation. 分类整理的知识蒸馏paper(2014-2021)。

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

mdetr. Python

Awesome-Visual-Transformer. Collect some papers about transformer with vision. Awesome Transformer with Computer Vision (CV)

spatio-temporal-contrastive-film. Unsupervised Film Genre Classification using Spatio-Temporal Contrastive Learning

copy-paste-aug. Copy-paste augmentation for segmentation and detection tasks

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

awesome-self-supervised-learning. A curated list of awesome self-supervised methods

awesome-contrastive-self-supervised-learning. A comprehensive list of awesome contrastive self-supervised learning papers.

WSL-Images. Weakly Supervised Learning On Images

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

simclr-converter. A PyTorch converter for SimCLR checkpoints

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

moco. PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722

SpineNet-Pytorch. SpineNet - mmdetection (Pytorch) Implementation

swav. PyTorch implementation of SwAV https//arxiv.org/abs/2006.09882

tide. A General Toolbox for Identifying Object Detection Errors

Awesome-of-Long-Tailed-Recognition. A curated list of long-tailed recognition resources.

VTHCL. [arXiv 2020] Video Representation Learning with Visual Tempo Consistency

video-nonlocal-net. Non-local Neural Networks for Video Classification

fashionpedia.

fashionpedia-api. Python API for Fashionpedia Dataset

noisystudent. Code for Noisy Student Training. https://arxiv.org/abs/1911.04252

SpineNet-Pytorch. This project is a kind of implementation of SpineNet(CVPR 2020) using mmdetection.

fucking-algorithm. Crack LeetCode, not only how, but also why.

PSIS. Data Augmentation for Object Detection via Progressive and Selective Instance-Switching

scene-representation-networks. Official Pytorch implementation of Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations

pytorch-metric-learning. The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

torchcv. TorchCV: A PyTorch-Based Framework for Deep Learning in Computer Vision

CutMix-PyTorch. Official Pytorch implementation of CutMix regularizer

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

LDAM-DRW. [NeurIPS 2019] Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss

EfficientNet-PyTorch. A PyTorch implementation of EfficientNet

Bag_of_Tricks_for_Image_Classification_with_Convolutional_Neural_Networks. experiments on Paper <Bag of Tricks for Image Classification with Convolutional Neural Networks> and other useful tricks to improve CNN acc

Class-balanced-loss-pytorch. Pytorch implementation of the paper "Class-Balanced Loss Based on Effective Number of Samples"

pytorch-cifar. 95.47% on CIFAR10 with PyTorch

mixup-cifar10. mixup: Beyond Empirical Risk Minimization

pytorch_compact_bilinear_pooling. Compact Bilinear Pooling for PyTorch

librosa. Python library for audio and music analysis

waymo-open-dataset. Waymo Open Dataset

sonnet. TensorFlow-based neural network library

lvis-api. Python API for LVIS Dataset

PointFlow. PointFlow : 3D Point Cloud Generation with Continuous Normalizing Flows

pyrobot. PyRobot: An Open Source Robotics Research Platform

xlnet. XLNet: Generalized Autoregressive Pretraining for Language Understanding

imat_fashion_comp. The iMaterialist Fashion Attribute Dataset

DeepFashion2. DeepFashion2 Dataset https://arxiv.org/pdf/1901.07973.pdf

modanet. ModaNet: A large-scale street fashion dataset with polygon annotations

kaggle-imaterialist. The First Place Solution of Kaggle iMaterialist (Fashion) 2019 at FGVC6

Made-With-ML. Learn how to develop, deploy and iterate on production-grade ML applications.

mujoco-py. MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.

imet-fgvcx.

SPADE. Semantic Image Synthesis with SPADE

cvpr18-caption-eval. Learning to Evaluate Image Captioning. CVPR 2018

class-balanced-loss. Class-Balanced Loss Based on Effective Number of Samples. CVPR 2019

cvpr18-inaturalist-transfer. Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning. CVPR 2018

transferlearning. Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习

PlotNeuralNet. Latex code for making neural networks diagrams

dataset-distillation. Open-source code for paper "Dataset Distillation"

GNNPapers. Must-read papers on graph neural networks (GNN)

graph_nets. Build Graph Nets in Tensorflow

deepcluster. Deep Clustering for Unsupervised Learning of Visual Features

pytext. A natural language modeling framework based on PyTorch

bert. TensorFlow code and pre-trained models for BERT

maskrcnn-benchmark. Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

vid2vid. Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.

mmdetection. OpenMMLab Detection Toolbox and Benchmark

mmcv. OpenMMLab Computer Vision Foundation

snca.pytorch. Improving Generalization via Scalable Neighborhood Component Analysis

TransferLearningClassification. Xuhong Li, Yves Grandvalet, and Franck Davoine. "Explicit Inductive Bias for Transfer Learning with Convolutional Networks." In ICML 2018.

pytorch-classification. Classification with PyTorch.

convnet-aig. PyTorch implementation for Convolutional Networks with Adaptive Inference Graphs

daily-paper-computer-vision. 记录每天整理的计算机视觉/深度学习/机器学习相关方向的论文

codalab-competitions. CodaLab Competitions

CatPapers. Cool vision, learning, and graphics papers on Cats!

dopamine. Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

self-critical.pytorch. Unofficial pytorch implementation for Self-critical Sequence Training for Image Captioning. and others.

3d-recon. Implementation for paper "Learning Single-View 3D Reconstruction with Limited Pose Supervision".

mmf. A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

pytorch-maml-rl. Reinforcement Learning with Model-Agnostic Meta-Learning in Pytorch

unbiased-offline-recommender-evaluation. Jupyter Notebook

talkthewalk. This repository provides code for reproducing experiments of the paper Talk The Walk: Navigating New York City Through Grounded Dialogue by Harm de Vries, Kurt Shuster, Dhruv Batra, Devi Parikh, Jason Weston, and Douwe Kiela.

DPNs. Dual Path Networks

intrinsic-dimension. Jupyter Notebook

lemniscate.pytorch. Unsupervised Feature Learning via Non-parametric Instance Discrimination

cmr. Project repo for Learning Category-Specific Mesh Reconstruction from Image Collections

explain_teach. Teaching Categories to Human Learners with Visual Explanations - CVPR 2018

Relation-Networks-for-Object-Detection. Relation Networks for Object Detection

SuperPointPretrainedNetwork. PyTorch pre-trained model for real-time interest point detection, description, and sparse tracking (https://arxiv.org/abs/1712.07629)

wechat_friends. 微信好友信息分析并可视化以及自动回复微信消息

hub. A library for transfer learning by reusing parts of TensorFlow models.

low-shot-shrink-hallucinate. Presenting Low-shot Visual Recognition by Shrinking and Hallucinating Features

CSrankings. A web app for ranking computer science departments according to their research output in selective venues, and for finding active faculty across a wide range of areas.

Selective-Joint-Fine-tuning. Codes and models for the CVPR 2017 spotlight paper "Borrowing Treasures from the Wealthy: Deep Transfer Learning through Selective Joint Fine-tuning".

seg_every_thing. Code release for Hu et al., Learning to Segment Every Thing. in CVPR, 2018.

CompactBilinearPooling-Pytorch. A Pytorch Implementation for Compact Bilinear Pooling.

Paper_Reading_List. Recommended Papers. Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Learning (cs.LG)

incubator-mxnet. Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

ELF. ELF: a platform for game research with AlphaGoZero/AlphaZero reimplementation

Foodx.

fgvcx_flower_comp.

readme2tex. Renders TeXy Math for Github Readme - No longer needed with official MathTex support on GH

fgvcx_fungi_comp. FGVCx Fungi Classfiication competition details

MUNIT. Multimodal Unsupervised Image-to-Image Translation

minigo. An open-source implementation of the AlphaGoZero algorithm

mxnet. Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

ava-dataset. The AVA dataset densely annotates 80 atomic visual actions in 351k movie clips with actions localized in space and time, resulting in 1.65M action labels with multiple labels per human occurring frequently.

CollMetric. A Tensorflow implementation of Collaborative Metric Learning (CML)

influence-release. Jupyter Notebook

inat_comp_2018. CNN training code for iNaturalist 2018 image classification competition

tpu. Reference models and tools for Cloud TPUs.

state-of-the-art-result-for-machine-learning-problems. This repository provides state of the art (SoTA) results for all machine learning problems. We do our best to keep this repository up to date. If you do find a problem's SoTA result is out of date or missing, please raise this as an issue or submit Google form (with this information: research paper name, dataset, metric, source code and year). We will fix it immediately.

julia. The Julia Programming Language

openrec. OpenRec is an open-source and modular library for neural network-inspired recommendation algorithms

Neural-Style-Transfer-Papers. :pencil2: Neural Style Transfer: A Review

Deformable-ConvNets. Deformable Convolutional Networks

Meta-Learning-Papers. Meta Learning / Learning to Learn / One Shot Learning / Few Shot Learning

Detectron. FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

relative_depth. Code for the NIPS 2016 paper

places-coco2017.github.io. Places + COCO Challenge

coco-analyze. A wrapper of the COCOeval class for extended keypoint error estimation analysis.

Mask_RCNN. Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

pyemd. [Deprecated; use POT instead] Fast EMD for Python: a wrapper for Pele and Werman's C++ implementation of the Earth Mover's Distance metric

handong1587.github.io. CSS

neural-editor. Repository for "Generating Sentences by Editing Prototypes"

gmn. Generative Matching Networks

cocodataset.github.io. HTML

SMASH. An experimental technique for efficiently exploring neural architectures.

SENet. Squeeze-and-Excitation Networks

tensorflow_compact_bilinear_pooling. Compact Bilinear Pooling in TensorFlow

DiscoGAN. Official implementation of "Learning to Discover Cross-Domain Relations with Generative Adversarial Networks"

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

models. Models and examples built with TensorFlow

tfrecords. Functions for creating tfrecords for TensorFlow models.

tf_classification. Training, evaluation and testing code for image classification using TensorFlow

imat_comp. iMaterialist (Fashion) Competition 2019

gym. A toolkit for developing and comparing reinforcement learning algorithms.

universe. Universe: a software platform for measuring and training an AI's general intelligence across the world's supply of games, websites and other applications.

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

pytorch_fft. PyTorch wrapper for FFTs

inat_comp_2017. CNN training code for iNaturalist 2017 image classification competition

cocostuff10k. The official homepage of the (outdated) COCO-Stuff 10K dataset.

Hard-Aware-Deeply-Cascaed-Embedding. source code for the paper "Hard-Aware-Deeply-Cascaed-Embedding"

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

signal. Signal Processing Library for PyTorch

pytorch-CycleGAN-and-pix2pix. Image-to-Image Translation in PyTorch

inat_comp. iNaturalist competition details

hugo. The world’s fastest framework for building websites.

kit. 🧱 Describe your site, AI builds it, you own it as Markdown. Snap together Tailwind blocks like Lego — landing pages, blogs, portfolios, docs & more. No AI slop. Free to deploy anywhere 👇

triplet-network-pytorch. Python

visdom. A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Torch and Numpy https://visdom.dev

awesome-deep-learning-papers. The most cited deep learning papers

show-attend-and-tell. TensorFlow Implementation of "Show, Attend and Tell"

ImageCaptioning.pytorch. I decide to sync up this repo and self-critical.pytorch. (The old master is in old master branch for archive)

the-incredible-pytorch. The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relating to PyTorch.