Twilight

G2. 📊 The concise and progressive visualization grammar.

kaji. The menu bar worth keeping for AI coding

RynnBrain. RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Models

numina-lean-agent. Python

clash-for-linux-install. 😼 优雅地使用基于 clash/mihomo 的代理环境

Harmonics. Hierarchical distribution matching enables comprehensive characterization of common and condition-specific cell niches in spatial omics data

GenesisGeo. Automatic solver for plane geometry problems.

repl. A simple REPL for Lean 4, returning information about errors and sorries.

tong-geometry. Python

alphageometry2. AlphaGeometry2 symbolic engine (DDAR) with examples

superhuman. Lean

circuit_sparsity. Open-source release accompanying Gao et al. 2025

textgrad. TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.

HAGeo.

NSFC-LaTex. BibTeX Style

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

InternSVG. [ICLR 2026] Official repository of "InternSVG: Towards Unified SVG Tasks with Multimodal Large Language Models".

PyTorch-SVGRender. SVG Differentiable Rendering: Generating vector graphics using neural networks. Support: text-to-SVG, Image-to-SVG, SVG Editing.

Awesome-Minecraft-Agent. Paper List of Minecraft Agents

discoveryworld. A virtual environment for developing and evaluating automated scientific discovery agents.

PyEuclid. [CAV 2025] PyEuclid: A Versatile Formal Plane Geometry System in Python

ios_rule_script. 分流规则、重写写规则及脚本。

formal-conjectures. A collection of formalized statements of conjectures in Lean.

Newclid. Automatic solver for plane geometry problems.

GDDM. Open Library of Geometry Automatic Theorem Provers

open-alphageometry. Python

ag4masses. Making Google Deepmind's AlphaGeometry accessible to the Masses

Elements. Greek/English version of Euclid's Elements

LeanEuclid. LeanEuclid is a benchmark for autoformalization in the domain of Euclidean geometry, targeting the proof assistant Lean.

R1-Onevision. R1-onevision, a visual language model capable of deep CoT reasoning.

lighteval. Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

compfiles. Catalog Of Math Problems Formalized In Lean

v2rayA-installer. A Installer of v2rayA

mathlib4. The math library of Lean 4

EG. Formalizing Euclidean Geometry in Lean

GeoCoq. A formalization of geometry in Coq based on Tarski's axiom system

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

HIF. Heterogeneous GNN Driven Information Prediction Framework

HERI-GCN. Python

leanblueprint. plasTeX plugin to build formalization blueprints.

show-rank. Extension for Google Chrome to show conference/journal rankings in search results. Currently supports CCF(China Computer Federation) rankings on Springer, DBLP, IEEExplore and ACM Digital Library.

Awesome-VLM-AD-ITS. [T-IV] This repository collects research papers of large Vision Language Models in Autonomous driving and Intelligent Transportation System. The repository will be continuously updated to track the latest update.

Qwen2.5-Math. A series of math-specific large language models of our Qwen2 series.

nanotron. Minimalistic large language model 3D-parallelism training

OLMo. Modeling, training, eval, and inference code for OLMo

ReProver. Retrieval-Augmented Theorem Provers for Lean

LeanDojo. Tool for data extraction and interacting with Lean programmatically.

cloth-segmentation. This repo contains code and a pre-trained model for clothes segmentation.

corenet. CoreNet: A library for training deep neural networks

Awesome-MLLM-Safety. Accepted by IJCAI-24 Survey Track

DeepSeek-Math. DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

dl4math. Resources of deep learning for mathematical reasoning (DL4MATH).

DL4TP. [COLM 2024] A Survey on Deep Learning for Theorem Proving

sam2. The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

linux_speed_test. To test ipv4 and ipv6 speed in linux.

LlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

HunyuanDiT. Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

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

Prompt-based-Distribution-Alignment. [AAAI 2024] Prompt-based Distribution Alignment for Unsupervised Domain Adaptation

CIM. [IJCAI'23] Complete Instances Mining for Weakly Supervised Instance Segmentation

SimMMDG. [NeurIPS 2023] SimMMDG: A Simple and Effective Framework for Multi-modal Domain Generalization

CoOp. Prompt Learning for Vision-Language Models (IJCV'22, CVPR'22)

LayoutGeneration. Python

rpasdt. RP&SDT (Rumour Rumour Propoagation and Source Detection Toolkit) is a tool that allows users to prepare and configure an initial network topology, a propagation process and utilize the well-known source identification algorithms to estimate real sources based on the given diffusion graph.

OpenAgents. [COLM 2024] OpenAgents: An Open Platform for Language Agents in the Wild

LLMsPracticalGuide. A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)

DM-GAN. Python

AI-For-Beginners. 12 Weeks, 24 Lessons, AI for All!

QiZhenGPT. QiZhenGPT: An Open Source Chinese Medical Large Language Model｜一个开源的中文医疗大语言模型

PureCLIPNeRF. Python

PaddleSleeve. PaddleSleeve

jax-cfd. Computational Fluid Dynamics in JAX

imageio-ffmpeg. FFMPEG wrapper for Python

ffmpeg-build-script. The FFmpeg build script provides an easy way to build a static FFmpeg on OSX and Linux with non-free codecs included.

multi-object-tracker. Multi-object trackers in Python

homebrew-ffmpeg. A homebrew tap for an ffmpeg formula with lots of options

MM-CelebA-HQ-Dataset. [CVPR 2021] Multi-Modal-CelebA-HQ: A Large-Scale Text-Driven Face Generation and Understanding Dataset

DeepEMD. Code for paper "DeepEMD: Few-Shot Image Classification with Differentiable Earth Mover's Distance and Structured Classifiers", CVPR2020

CMC. [arXiv 2019] "Contrastive Multiview Coding", also contains implementations for MoCo and InstDis

rfs. Python

SKD. SKD : Self-supervised Knowledge Distillation for Few-shot Learning

simclr. SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners

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

tfjs-tsne. TypeScript

multiple-objects-gan. Implementation for "Generating Multiple Objects at Spatially Distinct Locations" (ICLR 2019)

Obj-GAN. Obj-GAN - Official PyTorch Implementation

vimrc. The ultimate Vim configuration (vimrc)

SPADE. Semantic Image Synthesis with SPADE

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

exposure. Learning infinite-resolution image processing with GAN and RL from unpaired image datasets, using a differentiable photo editing model.

Exclusively-Dark-Image-Dataset. Exclusively Dark (ExDARK) dataset which to the best of our knowledge, is the largest collection of low-light images taken in very low-light environments to twilight (i.e 10 different conditions) to-date with image class and object level annotations.

deep-transfer-learning. A collection of implementations of deep domain adaptation algorithms

wassdistance. Approximating Wasserstein distances with PyTorch

distribution-is-all-you-need. The basic distribution probability Tutorial for Deep Learning Researchers

Deep-Photo-Enhancer. TensorFlow implementation of the CVPR 2018 spotlight paper, Deep Photo Enhancer: Unpaired Learning for Image Enhancement from Photographs with GANs

FastImageProcessing. Fast Image Processing with Fully-Convolutional Networks

wDAE_GNN_FewShot. Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learning

WideResNet-pytorch. Wide Residual Networks (WideResNets) in PyTorch

meta-transfer-learning. TensorFlow and PyTorch implementation of "Meta-Transfer Learning for Few-Shot Learning" (CVPR2019)

MetaOptNet. Meta-Learning with Differentiable Convex Optimization (CVPR 2019 Oral)

BF3S. Boosting Few-Shot Visual Learning with Self-Supervision

few-shot-ssl-public. Meta Learning for Semi-Supervised Few-Shot Classification

unsupervised-data-augmentation. Unofficial PyTorch Implementation of Unsupervised Data Augmentation.

EnlightenGAN. [IEEE TIP] "EnlightenGAN: Deep Light Enhancement without Paired Supervision" by Yifan Jiang, Xinyu Gong, Ding Liu, Yu Cheng, Chen Fang, Xiaohui Shen, Jianchao Yang, Pan Zhou, Zhangyang Wang

image-quality-assessment. Convolutional Neural Networks to predict the aesthetic and technical quality of images.

AutoAugment. Unofficial implementation of the ImageNet, CIFAR 10 and SVHN Augmentation Policies learned by AutoAugment using pillow

fast-autoaugment. Official Implementation of 'Fast AutoAugment' in PyTorch.

UDA-pytorch. Unsupervised Data Augmentation experiments in PyTorch

uda. Unsupervised Data Augmentation (UDA)

RNAN. PyTorch code for our ICLR 2019 paper "Residual Non-local Attention Networks for Image Restoration"

wide-resnet.pytorch. Best CIFAR-10, CIFAR-100 results with wide-residual networks using PyTorch

wide-residual-networks. 3.8% and 18.3% on CIFAR-10 and CIFAR-100

dgl. Python package built to ease deep learning on graph, on top of existing DL frameworks.

netdata. The fastest path to AI-powered full stack observability, even for lean teams.

fastText. Library for fast text representation and classification.

umap. Uniform Manifold Approximation and Projection

MUNIT. Multimodal Unsupervised Image-to-Image Translation

SceneGraph. Scene Graphs with Permutation-Invariant Structured Prediction

FEAT. The code repository for "Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions"

pybrisque. A python implementation of BRISQUE Image Quality Assessment

pytorch-ssim. pytorch structural similarity (SSIM) loss

PerceptualSimilarity. LPIPS metric. pip install lpips

FewShotWithoutForgetting. Python

CloserLookFewShot. source code to ICLR'19, 'A Closer Look at Few-shot Classification'

prototypical-networks. Code for the NeurIPS 2017 Paper "Prototypical Networks for Few-shot Learning"

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

FeatureLearningRotNet. Python

DRIT. Learning diverse image-to-image translation from unpaired data

parsimonious-blackbox-attack. Official TensorFlow implementation of "Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimization" (ICML 2019)

cleverhans. An adversarial example library for constructing attacks, building defenses, and benchmarking both

pytorch_geometric. Graph Neural Network Library for PyTorch

universal. Matlab

small_norb. Python wrapper to small NORB dataset

UNIT. Unsupervised Image-to-Image Translation

singular-fool. Universal Adversarial Perturbations based on the (p, q)-singular vectors.

mnist_challenge. A challenge to explore adversarial robustness of neural networks on MNIST.

MUNIT-Tensorflow. Simple Tensorflow implementation of "Multimodal Unsupervised Image-to-Image Translation" (ECCV 2018)

tensorflow-adversarial. Crafting adversarial images

adversarial-examples. Adversarial Examples: Attacks and Defenses for Deep Learning

stAdv. Spatially Transformed Adversarial Examples with TensorFlow

adversarial-examples-pytorch. Implementation of Papers on Adversarial Examples

pytorch-summary. Model summary in PyTorch similar to `model.summary()` in Keras

996.ICU. Repo for counting stars and contributing. Press F to pay respect to glorious developers.

tsne-cuda. GPU Accelerated t-SNE for CUDA with Python bindings

CycleGAN-Tensorflow. A Tensorflow implementation of Cycle-Consistent Adversarial Networks.

deepcluster. Deep Clustering for Unsupervised Learning of Visual Features

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

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

PRML. Pattern recognition and machine learning toolbox

DCPDN. Densely Connected Pyramid Dehazing Network (CVPR'2018)

Learning-to-See-in-the-Dark. Learning to See in the Dark. CVPR 2018

MegaDepth. Code of single-view depth prediction algorithm on Internet Photos described in "MegaDepth: Learning Single-View Depth Prediction from Internet Photos, Z. Li and N. Snavely, CVPR 2018".

DeepGuidedFilter. Official Implementation of Fast End-to-End Trainable Guided Filter, CVPR 2018

use_vim_as_ide. use vim as IDE

machine-learning-notes. My continuously updated Machine Learning, Probabilistic Models and Deep Learning notes and demos (2000+ slides) 我不间断更新的机器学习，概率模型和深度学习的讲义(2000+页)和视频链接

pytorch-spectral-normalization-gan. Paper by Miyato et al. https://openreview.net/forum?id=B1QRgziT-

Progressive_Growing_of_GANs-PyTorch. A PyTorch 0.4 implementation of Progressive Growing of GANs for Improved Quality, Stability and Variability (https://arxiv.org/abs/1710.10196)

tensorboardX. tensorboard for pytorch (and chainer, mxnet, numpy, ...)

pytorch-fid. Compute FID scores with PyTorch.

pytorch-tutorial. PyTorch Tutorial for Deep Learning Researchers

Unsupervised-Attention-guided-Image-to-Image-Translation. Unsupervised Attention-Guided Image to Image Translation

metric-learning. Use metric learning to cluster images and run similar image queries

Text-to-Image-Synthesis. Pytorch implementation of Generative Adversarial Text-to-Image Synthesis paper

examples. A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

PyTorch-GAN. PyTorch implementations of Generative Adversarial Networks.

StackGAN-Pytorch. Python

tensorflow-GANs. 各类GAN综合在一起，借鉴了hwalsuklee大神的

text-to-image. Re-implementation of https://github.com/zsdonghao/text-to-image

snap. Stanford Network Analysis Platform (SNAP) is a general purpose network analysis and graph mining library.

pytorch-playground. Base pretrained models and datasets in pytorch (MNIST, SVHN, CIFAR10, CIFAR100, STL10, AlexNet, VGG16, VGG19, ResNet, Inception, SqueezeNet)

k-means. C++ implements k-means algorithm

cnn-text-classification-tf. Convolutional Neural Network for Text Classification in Tensorflow

twapy. Temporal Word Analogies in Python

efanna. fast library for ANN search and KNN graph construction

Multicore-TSNE. Parallel t-SNE implementation with Python and Torch wrappers.

LargeVis. C++

dl-traffic. Code for the "Deep Learning for Short-Term Traffic Flow Prediction" paper (https://arxiv.org/abs/1604.04527)

awesome-2vec. Curated list of 2vec-type embedding models

NRLPapers. Must-read papers on network representation learning (NRL) / network embedding (NE)

markvis. make visualization in markdown. 📊📈

Shadowrocket.