Pomelo

Explainable-AI-in-Financial-Fraud-and-Anomaly-Detection. This repository explores explainable deep learning models for financial fraud detection and anomaly analysis. It integrates Graph Neural Networks (GNNs), Autoencoders, and SHAP-based explainability to identify and interpret fraudulent behaviors in transactional data.

rp-engine. YAML-native agent workflow execution engine, written in Rust

Psi0. [RSS26'] Welcome to Psi-Zero, a Humanoid VLA towards Universal Humanoid Intelligence.

Coglet. Will Cogley's DIY Desktop Companion for Makers

openakita. An open-source AI assistant framework with skills and agent architecture

dingtalk-openclaw-connector. Official OpenClaw DingTalk channel plugin | 钉钉官方 OpenClaw 插件

awesome-LLM-resources. 🧑‍🚀 全世界最好的LLM资料总结（多模态生成、Agent、辅助编程、AI审稿、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型） | Summary of the world's best LLM resources.

Figure-Skating-Choreography-. Analyze entered music files based on its BPM, and then generate a figure skating choreography plan according to the analysis results.

ICML25-DPCR. Official implementation of Semantic Shift Estimation via Dual-Projection and Classifier Reconstruction for Exemplar-Free Class-Incremental Learning (ICML25).

chatgpt-prompts-for-academic-writing. This list of writing prompts covers a range of topics and tasks, including brainstorming research ideas, improving language and style, conducting literature reviews, and developing research plans.

Analytic-Continual-Test-Time-Adaptation-for-Multi-Modality-Corruption. Python

Hunyuan3D-2. High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

happy-llm. 📚 从零开始构建大模型

llm-action. 本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

LLMForEverybody. 每个人都能看懂的大模型知识分享，LLMs春/秋招大模型面试前必看，让你和面试官侃侃而谈

minimind. 🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!

Any-SSR. This is the official code for Any-SSR "Analytic Subspace Routing: How Recursive Least Squares Works in Continual Learning of Large Language Model"

wina. ICLR 2026

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

MIAA_SIM. 这是一个机器人的简单仿真环境

dify. Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.

ColossalAI. Making large AI models cheaper, faster and more accessible

llm_rl. llm & rl

GPT_API_free. Free ChatGPT&DeepSeek API Key，免费ChatGPT&DeepSeek API。免费接入DeepSeek API和GPT4 API，支持 gpt | deepseek | claude | gemini | grok 等排名靠前的常用大模型。

coursera-deep-learning-specialization. Notes, programming assignments and quizzes from all courses within the Coursera Deep Learning specialization offered by deeplearning.ai: (i) Neural Networks and Deep Learning; (ii) Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization; (iii) Structuring Machine Learning Projects; (iv) Convolutional Neural Networks; (v) Sequence Models

info8010-deep-learning. Lectures for INFO8010 Deep Learning, ULiège

Neural-Network-Diffusion. We introduce a novel approach for parameter generation, named neural network parameter diffusion (p-diff), which employs a standard latent diffusion model to synthesize a new set of parameters

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

Regression-based-Analytic-Incremental-Learning. Python

Awesome-Continual-Learning. A curated list of Continual Learning papers and BibTeX entries

O1-Journey. O1 Replication Journey

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

RLBench. A large-scale benchmark and learning environment.

ReKep. ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation

awesome-instruction-datasets. A collection of awesome-prompt-datasets, awesome-instruction-dataset, to train ChatLLM such as chatgpt 收录各种各样的指令数据集, 用于训练 ChatLLM 模型。

Odyssey. Odyssey: Empowering Minecraft Agents with Open-World Skills

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

PyPOTS. A Python toolkit/library for reality-centric machine/deep learning & data mining on partially-observed time series, with 50+ SOTA neural network models for scientific analysis tasks (imputation, classification, clustering, forecasting, anomaly detection, cleaning) on incomplete industrial irregularly-sampled multivariate TS with NaN missing values

time-series-ptms. This is an official implementation code for paper "A Survey on Time-Series Pre-Trained Models" (TKDE-24).

ragflow. RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

al-folio. A beautiful, simple, clean, and responsive Jekyll theme for academics

Analytic-federated-learning. This repo will be continually updating analytic federated learning methods.

BlackboardCaptor. A mobile application that can help users get the perfect blackboard photos.

llama3. The official Meta Llama 3 GitHub site

mqcloud. RocketMQ企业级一站式服务平台

bizspring-shop-opensource. BizSpring Java商城首选,可商用；Vue3,Element UI Plus,Uniapp,微服务,SpringCloud,跨境电商,跨境商城,电商国际化,外贸,独立站,多国语言,移动商城,小程序商城,H5商城,公众号商城,App,Redis,支持多语言,多规格SKU,分销,拼团,砍价,秒杀,优惠券,积分,会员等级,小程序前后端分离,方便二开,Markdown在线文档,代码生成,二开文档齐全,代码规范

webrtc-streamer-helper. webrtc streamer helper

github-monthly-rank. Github开源项目:每月📈飙升榜 top30,每月1号早上8点更新

cachecloud. 搜狐视频(sohu tv)Redis私有云平台 ：支持Redis多种架构(Standalone、Sentinel、Cluster)高效管理、有效降低大规模redis运维成本，提升资源管控能力和利用率。平台提供快速搭建/迁移，运维管理，弹性伸缩，统计监控，客户端整合接入等功能。(CacheCloud is a Redis cloud management platform. It supports Standalone, Sentinel, and Cluster architectures for Redis, effectively reducing large-scale Redis operation and maintenance costs, and improving resource management and utilization. The platform provides rapid construction/migration, operation and maintenance management, elastic scaling, statistical monitoring, client integration and access and other functions)

long-form-factuality. Benchmarking long-form factuality in large language models. Original code for our paper "Long-form factuality in large language models".

umi-gripper.github.io. SCSS

FedML. FEDML - The unified and scalable ML library for large-scale distributed training, model serving, and federated learning. FEDML Launch, a cross-cloud scheduler, further enables running any AI jobs on any GPU cloud or on-premise cluster. Built on this library, TensorOpera AI (https://TensorOpera.ai) is your generative AI platform at scale.

act-plus-plus. Imitation learning algorithms with Co-training for Mobile ALOHA: ACT, Diffusion Policy, VINN

iVoro. ICLR 2023

starting-kit. Starting kit for the NeurIPS 2023 unlearning challenge

image-similarity-deep-ranking. Python

image-similarity-using-deep-ranking. 🖼️ 𝖀𝖓𝖔𝖋𝖋𝖎𝖈𝖎𝖆𝖑 PyTorch implementation of "Learning Fine-grained Image Similarity with Deep Ranking" (arXiv:1404.4661)

image-matching-triplet-loss. Tensorflow implementation of Image Matching with Triplet Loss on the Tiny ImageNet dataset.

Instruct2Act. Instruct2Act: Mapping Multi-modality Instructions to Robotic Actions with Large Language Model

recognize-anything. Open-source and strong foundation image recognition models.

GroundingDINO. [ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

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

Next-Generation-AI-awesome. An up-to-date list of progress made in next-generation AI.

alpaca-lora. Instruct-tune LLaMA on consumer hardware

image_triplet_loss. Image similarity using Triplet Loss

FCAC. Few-shot class-incremental audio classification, which can continually recognize novel audio classes without forgetting old ones

Awesome-Few-Shot-Class-Incremental-Learning. Awesome Few-Shot Class-Incremental Learning

ImageBind. ImageBind One Embedding Space to Bind Them All

safe-rlhf. Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

OpenGPT. A framework for creating grounded instruction based datasets and training conversational domain expert Large Language Models (LLMs).

InternImage. [CVPR 2023 Highlight] InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions

FSCIL. [ICLR 2023] The official code for our ICLR 2023 (top25%) paper: "Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class-Incremental Learning"

pandallm. Panda项目是于2023年5月启动的开源海外中文大语言模型项目，致力于大模型时代探索整个技术栈，旨在推动中文自然语言处理领域的创新和合作。

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

FastChat. An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

llama. Inference code for Llama models

stanford_alpaca. Code and documentation to train Stanford's Alpaca models, and generate the data.

street-fighter-ai. This is an AI agent for Street Fighter II Champion Edition.

Open-Assistant. OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

ChatGenTitle. 🌟 ChatGenTitle：使用百万arXiv论文信息在LLaMA模型上进行微调的论文题目生成模型

uvadlc_notebooks. Repository of Jupyter notebook tutorials for teaching the Deep Learning Course at the University of Amsterdam (MSc AI), Fall 2023

Vitis-AI. Vitis AI is Xilinx’s development stack for AI inference on Xilinx hardware platforms, including both edge devices and Alveo cards.

gpt4all. GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

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.

Analytic-continual-learning. This repository will be posting analytic continual learning series, including Analytic Class-Incremental Learning (ACIL), Gaussian Kernel Embedded Analytic Learning (GKEAL), Dual-Stream Analytic Learning (DS-AL), etc.

CRNet. Official Implementation of "CRNet: A Fast Continual Learning Framework with Random Theory" paper

Alpaca-CoT. We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tuning) together for easy use. We welcome open-source enthusiasts to initiate any meaningful PR on this repo and integrate as many LLM related technologies as possible. 我们打造了方便研究人员上手和使用大模型等微调平台，我们欢迎开源爱好者发起任何有意义的pr！

TaskMatrix. Python

mm-cot. Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)

FCIL. This is the formal code implementation of the CVPR 2022 paper 'Federated Class Incremental Learning'.

FlexCNN. C++

bgd. Implementation of Bayesian Gradient Descent

OCM. Python

IL2A. PyTorch implementation of our NeurIPS 2021 paper "Class-Incremental Learning via Dual Augmentation"

mammoth. An Extendible (General) Continual Learning Framework based on Pytorch - official codebase of Dark Experience for General Continual Learning

dytox. Dynamic Token Expansion with Continual Transformers, accepted at CVPR 2022

l2p. Learning to Prompt (L2P) for Continual Learning @ CVPR22 and DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning @ ECCV22

GCAB-CFDC. Official Implementation of the paper "Exemplar-free Continual Learning of Vision Transformers via Gated Class-Attention and Cascaded Feature Drift Compensation"

online-continual-learning. A collection of online continual learning paper implementations and tricks for computer vision in PyTorch, including our ASER(AAAI-21), SCR(CVPR21-W) and survey (Neurocomputing).

pretrained-models-in-CL. Official repository for Do Pre-trained Models Benefit Equally in Continual Learning? (Accepted to WACV'23)

alphatensor. Python

ERD. Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillation

t-SNE-tutorial. A tutorial on the t-SNE learning algorithm

constrained-FSCIL. PyTorch Implementation of the CVPR'22 Paper "Constrained Few-shot Class-incremental Learning"

SPR. Official Repository for our ICCV2021 paper: Continual Learning on Noisy Data Streams via Self-Purified Replay

exploring_the_limits_of_OOD_detection. Code to replicate the key results from Exploring the Limits of Out-of-Distribution Detection (https://arxiv.org/abs/2106.03004) by Stanislav Fort, Jie Ren, Balaji Lakshminarayanan, published at NeurIPS 2021.

iMTFA. Code accompanying the paper 'Incremental Few-Shot Instance Segmentation'

iOD. (TPAMI 2021) iOD: Incremental Object Detection via Meta-Learning

CLOM. Python

CVPR22-Fact. Forward Compatible Few-Shot Class-Incremental Learning (CVPR'22)

d2l-zh. 《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。

Lihang. Statistical learning methods, 统计学习方法(第2版)[李航] [笔记, 代码, notebook, 参考文献, Errata, lihang]

F2M. Python

multi-label-ood. Python

MOOD. Code for CVPR2021 paper: MOOD: Multi-level Out-of-distribution Detection

FDG. Fully Decoupled Neural Network Learning Using Delayed Gradients (FDG)

CEC-CVPR2021. Pytorch code for CVPR2021 paper "Few-Shot Incremental Learning with Continually Evolved Classifiers"

causalml. Uplift modeling and causal inference with machine learning algorithms

GDN. Implementation code for the paper "Graph Neural Network-Based Anomaly Detection in Multivariate Time Series" (AAAI 2021)

incremental_learning.pytorch. A collection of incremental learning paper implementations including PODNet (ECCV20) and Ghost (CVPR-W21).

OODSurvey. The Official Repository for "Generalized OOD Detection: A Survey"

fscil. Official repository for Few-Shot Class-Incremental Learning (FSCIL)

class-incremental-learning. PyTorch implementation of AANets (CVPR 2021) and Mnemonics Training (CVPR 2020 Oral)

Awesome-Incremental-Learning. Awesome Incremental Learning

odin. A simple and effective method for detecting out-of-distribution images in neural networks.

energy_ood. Python

Reinforcement-Learning-in-Robotics. This is a private learning repository for reinforcement learning techniques used in robotics.

bolt. 10x faster matrix and vector operations

YOLOX. YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

One-Class-Kernel-ELM. MATLAB

SKAB. SKAB - Skoltech Anomaly Benchmark. Time-series data for evaluating Anomaly Detection algorithms.

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

Swin-Transformer. This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

DPT. Dense Prediction Transformers

facemask-detector. Face Mask Detection in PyTorch

Face-Mask-Detection-Pytorch. Jupyter Notebook

FaceMaskDetection. 开源人脸口罩检测模型和数据 Detect faces and determine whether people are wearing mask.

DDE_CIL. Python

leetcode. Python & JAVA Solutions for Leetcode

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

ifsl. [NeurIPS 2020] Released code for Interventional Few-Shot Learning

CBS. Curriculum by Smoothing (NeurIPS 2020)

Beta-VAE. Pytorch implementation of β-VAE

FactorVAE. Pytorch implementation of FactorVAE proposed in Disentangling by Factorising(http://arxiv.org/abs/1802.05983)

awesome-causality-algorithms. An index of algorithms for learning causality with data

pytorch-grad-cam. Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

pearl-primer. Notes for Judea Pearl et al., *Causal Inference in Statistics, a Primer*

classifier-balancing. This repository contains code for the paper "Decoupling Representation and Classifier for Long-Tailed Recognition", published at ICLR 2020

Long-Tailed-Recognition.pytorch. [NeurIPS 2020] This project provides a strong single-stage baseline for Long-Tailed Classification, Detection, and Instance Segmentation (LVIS). It is also a PyTorch implementation of the NeurIPS 2020 paper 'Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect'.

automl. Google Brain AutoML

TResNet. Official Pytorch Implementation of "TResNet: High-Performance GPU-Dedicated Architecture" (WACV 2021)

yolov5-comment. yolov5的注释版本

CDCL-human-part-segmentation. Repository for Paper: Cross-Domain Complementary Learning Using Pose for Multi-Person Part Segmentation (TCSVT20)

Face-Detection. Face detection with darknet on WIDER FACE

dvc. 🦉 Data Versioning and ML Experiments

netron. Visualizer for neural network, deep learning and machine learning models

thesis_template_ntu. Thesis Latex Template for Nanyang Technological University (NTU)

bottleneck-transformer-pytorch. Implementation of Bottleneck Transformer in Pytorch

tensorwatch. Debugging, monitoring and visualization for Python Machine Learning and Data Science

InfoPro-Pytorch. Learning recognition/segmentation models without end-to-end training. 40%-60% less GPU memory footprint. Same training time. Better performance.

T2T-ViT. ICCV2021, Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet

yolov5. Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.

ScaledYOLOv4. Scaled-YOLOv4: Scaling Cross Stage Partial Network

sacred. Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.

RepVGG. RepVGG: Making VGG-style ConvNets Great Again

FaceX-Zoo. A PyTorch Toolbox for Face Recognition

Deformable-DETR. Deformable DETR: Deformable Transformers for End-to-End Object Detection.

pytorch-image-models. The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

sam. SAM: Sharpness-Aware Minimization (PyTorch)

tencent-ml-images. Largest multi-label image database; ResNet-101 model; 80.73% top-1 acc on ImageNet

vit-pytorch. Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

vision_transformer. Jupyter Notebook

mmdetection. OpenMMLab Detection Toolbox and Benchmark

switch-cuda. A simple bash script for switching between installed versions of CUDA.

awesome-face-detection. face_detection_paper_code

vedadet. A single stage object detection toolbox based on PyTorch

SRN. Selective Refinement Network for High Performance Face Detection, AAAI, 2019

Face-Detector-1MB-with-landmark. 1M人脸检测模型(含关键点)

Real-World-Masked-Face-Dataset. Real-World Masked Face Dataset，口罩人脸数据集

awesome-cheatsheets. 👩‍💻👨‍💻 Awesome cheatsheets for popular programming languages, frameworks and development tools. They include everything you should know in one single file.

lsc-cnn. Python

Awesome-Multi-Task-Learning. A list of multi-task learning papers and projects.

FairMOT. [IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking

mtan. The implementation of "End-to-End Multi-Task Learning with Attention" [CVPR 2019].

Multi-Task-Learning-PyTorch. PyTorch implementation of multi-task learning architectures, incl. MTI-Net (ECCV2020).

Deep-Learning-without-Weight-Transport. Deep Learning without Weight Transport

FedMA. Code for Federated Learning with Matched Averaging, ICLR 2020.

awesome-federated-learning. All materials you need for Federated Learning: blogs, videos, papers, and softwares, etc.

LocalSGD-Code. Python

LocalSGD-Code.

torchgpipe. A GPipe implementation in PyTorch

face-mask. Wear face masks in the given picture.

video-object-removal. Just draw a bounding box and you can remove the object you want to remove.

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

faster-rcnn.pytorch. A faster pytorch implementation of faster r-cnn

pytorch-YOLOv4. PyTorch ,ONNX and TensorRT implementation of YOLOv4

DBFace. DBFace is a real-time, single-stage detector for face detection, with faster speed and higher accuracy

Gradient-Centralization. A New Optimization Technique for Deep Neural Networks

facenet-pytorch. Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models

Pytorch_Retinaface. Retinaface get 80.99% in widerface hard val using mobilenet0.25.