zhangyongshun

awesome-ai-agent-papers. A curated collection of AI agent research papers released in 2026, covering agent engineering, memory, evaluation, workflows, and autonomous systems.

Awesome-AgenticLLM-RL-Papers.

MUG-V. MUG-V 10B: High-efficiency Training Pipeline for Large Video Generation Models

RAE. Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"

T2I-Generation-Paper-List. Tracking the latest and greatest research papers on text-to-image generation.

system_prompts_leaks. Extracted system prompts from Anthropic - Claude Fable 5, Opus 5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-5.6-Sol, Codex. Google - Gemini 3.5 Flash, 3.1 Pro, Antigravity. xAI - Grok, Cursor, Copilot, VS Code, Perplexity, and more. Updated regularly.

ms-swift. Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).

Ovis-U1. An unified model that seamlessly integrates multimodal understanding, text-to-image generation, and image editing within a single powerful framework.

Wan2.1. Wan: Open and Advanced Large-Scale Video Generative Models

VACE. [ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing

OmniGen. OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

mochi. The best OSS video generation models, created by Genmo

CogVLM2. GPT4V-level open-source multi-modal model based on Llama3-8B

Kolors. Kolors Team

Atomic_Feature_Mimicking. This is an official implementation for "Unified Low-rank Compression Framework for Click-through Rate Prediction".

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

MGM. Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"

StreamingT2V. [CVPR 2025] StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text

tiktoken. tiktoken is a fast BPE tokeniser for use with OpenAI's models.

ToMe. A method to increase the speed and lower the memory footprint of existing vision transformers.

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

LAVIS. LAVIS - A One-stop Library for Language-Vision Intelligence

mistral-inference. Official inference library for Mistral models

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

langchain. The agent engineering platform.

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

DeepSpeed. DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

PaddleClas. A treasure chest for visual classification and recognition powered by PaddlePaddle

davit. [ECCV 2022]Code for paper "DaViT: Dual Attention Vision Transformer"

FasterTransformer. Transformer related optimization, including BERT, GPT

TensorRT. PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT

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

Deep_Metric. Deep Metric Learning

UP-ViT. This is an official implementation for "A Unified Pruning Framework for Vision Transformers".

YOLOU. YOLOv3、YOLOv4、YOLOv5、YOLOv5-Lite、YOLOv6-v1、YOLOv6-v2、YOLOv7、YOLOX、YOLOX-Lite、PP-YOLOE、PP-PicoDet-Plus、YOLO-Fastest v2、FastestDet、YOLOv5-SPD、TensorRT、NCNN、Tengine、OpenVINO

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

fast-reid. SOTA Re-identification Methods and Toolbox

examples. Example deep learning projects that use wandb's features.

Awesome-Model-Quantization. A list of papers, docs, codes about model quantization. This repo is aimed to provide the info for model quantization research, we are continuously improving the project. Welcome to PR the works (papers, repositories) that are missed by the repo.

accelerate. 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

shrinkbench. PyTorch library to facilitate development and standardized evaluation of neural network pruning methods.

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

mmpretrain. OpenMMLab Pre-training Toolbox and Benchmark

BagofTricks-LT. A scientific and useful toolbox, which contains practical and effective long-tail related tricks with extensive experimental results

NJUThesis. 南京大学学位论文模板

mmcv. OpenMMLab Computer Vision Foundation

mmdet-yolov4. Python

ssl_detection. Semi-supervised learning for object detection

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/

mmdetection. OpenMMLab Detection Toolbox and Benchmark

BYOL-PyTorch. PyTorch implementation of "Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning" with DDP and Apex AMP

simsiam. PyTorch implementation of SimSiam https//arxiv.org/abs/2011.10566

byol-pytorch. Usable Implementation of "Bootstrap Your Own Latent" self-supervised learning, from Deepmind, in Pytorch

awesome-long-tail-learning.

awesome-cbir-papers. 📝Awesome and classical image retrieval papers

Long-Tailed-Classification-Leaderboard.

tips_for_interview. 我的一些面试心得；自学CS历程分享；找工作求职经验分享

NRS_pytorch. Neural Random Subspace (NRS) official pytorch implementation

mwh. Python

Awesome-Pruning. A curated list of neural network pruning resources.

darknet. YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )

CPlusPlusThings. C++那些事

DeepLearning-500-questions. 深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为18个章节，50余万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系scutjy2015@163.com 版权所有，违权必究 Tan 2018.06

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

CENet. Channel Equilibrium Networks for Learning Deep Representation, ICML2020

Face_Pytorch. face recognition algorithms in pytorch framework, including arcface, cosface, sphereface and so on

numpy. The fundamental package for scientific computing with Python.

CURL. PyTorch Implementation of CURL-Neural Network Pruning with Residual-Connections and Limited-Data

AutoPruner. PyTorch Implementation of AutoPruner

MetaPruning. MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning. In ICCV 2019.

slimmable_networks. Slimmable Networks, AutoSlim, and Beyond, ICLR 2019, and ICCV 2019

onnx_tflite_yolov3. A Conversion tool to convert YOLO v3 Darknet weights to TF Lite model (YOLO v3 PyTorch > ONNX > TensorFlow > TF Lite), and to TensorRT (YOLO v3 Pytorch > ONNX > TensorRT).

deep-learning-model-convertor. The convertor/conversion of deep learning models for different deep learning frameworks/softwares.

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

SKU110K_CVPR19. Python

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

MobileNetV2-PyTorch. This is the PyTorch implement of MobileNet V2

mobilenetv2.pytorch. 72.8% MobileNetV2 1.0 model on ImageNet and a spectrum of pre-trained MobileNetV2 models

eql.detectron2. The official implementation of Equalization Loss for Long-Tailed Object Recognition (CVPR 2020) based on Detectron2. https://arxiv.org/abs/2003.05176

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

ssds.pytorch. Repository for Single Shot MultiBox Detector and its variants, implemented with pytorch, python3.

Yet-Another-EfficientDet-Pytorch. The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.

ImageNetV2. A new test set for ImageNet

AFN. (ICCV'19 Best Paper Nomination) Larger Norm More Transferable: An Adaptive Feature Norm Approach for Unsupervised Domain Adaptation

IndRNN_pytorch. Independently Recurrent Neural Networks (IndRNN) implemented in pytorch.

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

filter-pruning-geometric-median. Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration (CVPR 2019 Oral)

geo_prior. Presence-Only Geographical Priors for Fine-Grained Image Classification - ICCV 2019

assembled-cnn. Tensorflow implementation of "Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network"

dropblock. Implementation of DropBlock: A regularization method for convolutional networks in PyTorch.

stylize-datasets. A script that applies the AdaIN style transfer method to arbitrary datasets

Switchable-Whitening. Code for Switchable Whitening (ICCV2019)

texture-vs-shape. Pre-trained models, data, code & materials from the paper "ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness" (ICLR 2019 Oral)

RG-SENet_SP-SENet. PyTorch implementation of Delving Deep into Spatial Pooling for Squeeze-and-Excitation Networks.

ED-Net. PyTorch implementation of A Lightweight Encoder-Decoder Path for Deep Residual Networks.

convert_torch_to_pytorch. Convert torch t7 model to pytorch model and source.

darknet. Convolutional Neural Networks

pytorch. Tensors and Dynamic neural networks in Python with strong GPU acceleration

ThiNet. caffe model of ICCV'17 paper - ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression https://arxiv.org/abs/1707.06342

local-loss. PyTorch code for training neural networks without global back-propagation

proxylessnas. [ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

resnet_finetune_cub. Fine tuning Codes for ResNet on cub-200-2011

manifold_mixup. Code for reproducing Manifold Mixup results (ICML 2019)

CostSensitiveClassification. CostSensitiveClassification Library in Python

imbalanced-dataset-sampler. A (PyTorch) imbalanced dataset sampler for oversampling low frequent classes and undersampling high frequent ones.

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

Awesome-Learning-with-Label-Noise. A curated list of resources for Learning with Noisy Labels

valid-oversample. Valid Oversampling Schemes to Handle Imbalance

noisy_labels. TRAINING DEEP NEURAL-NETWORKS USING A NOISE ADAPTATION LAYER

learn-with-noisy-labels. Python

PENCIL. PyTorch implementation of Probabilistic End-to-end Noise Correction for Learning with Noisy Labels, CVPR 2019.

LightCNN. A Light CNN for Deep Face Representation with Noisy Labels, TIFS 2018

siamese-triplet. Siamese and triplet networks with online pair/triplet mining in PyTorch

noisy_label. Code for the CVPR15 paper "Learning from Massive Noisy Labeled Data for Image Classification"

Learning-from-web-data. Learning from web data for image classification

DCL. Destruction and Construction Learning for Fine-grained Image Recognition

fast-MPN-COV. @CVPR2018: Efficient unrolling iterative matrix square-root normalized ConvNets, implemented by PyTorch (and code of B-CNN,Compact bilinear pooling etc.) for training from scratch & finetuning.

manifold-diffusion. Diffusion on manifolds for image retrieval

cnnimageretrieval-pytorch. CNN Image Retrieval in PyTorch: Training and evaluating CNNs for Image Retrieval in PyTorch

DeLF-pytorch. PyTorch Implementation of "Large-Scale Image Retrieval with Attentive Deep Local Features"

dual_encoding. [CVPR2019] Dual Encoding for Zero-Example Video Retrieval

Humpback-Whale-Identification-1st-. https://www.kaggle.com/c/humpback-whale-identification

ms-powder. Multispectral Imaging for Fine-Grained Recognition of Powders on Complex Backgrounds (CVPR 2019)

OpenLongTailRecognition-OLTR. Pytorch implementation for "Large-Scale Long-Tailed Recognition in an Open World" (CVPR 2019 ORAL)

VAE-CVAE-MNIST. Variational Autoencoder and Conditional Variational Autoencoder on MNIST in PyTorch

pytorch_VAE_CVAE. pytorch implementation Variational Autoencoder and Conditional Variational Autoencoder

CVAE-GAN. Python

pytorch-GANs. Various GANs in pytorch environment

reid-strong-baseline. Bag of Tricks and A Strong Baseline for Deep Person Re-identification

NAS-Papers. Paper list of network architecture search (NAS)

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

person-re-ranking. Person Re-ranking (CVPR 2017)

MARS-evaluation. This repository provides the evaluation codes for the MARS dataset

pytorch_Realtime_Multi-Person_Pose_Estimation. Python

Realtime_Multi-Person_Pose_Estimation. Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)

human-pose-estimation.pytorch. The project is an official implement of our ECCV2018 paper "Simple Baselines for Human Pose Estimation and Tracking(https://arxiv.org/abs/1804.06208)"

senet.pytorch. PyTorch implementation of SENet

CAM. Class Activation Mapping

pytorch-template. PyTorch deep learning projects made easy.

pytorch-template. My PyTorch project template (for Kaggle and research)

PointCNN. PointCNN: Convolution On X-Transformed Points (NeurIPS 2018)

confusion. Code for the ECCV 2018 paper "Pairwise Confusion for Fine-Grained Visual Classification"

pipeline. Python

deepcluster. Deep Clustering for Unsupervised Learning of Visual Features

Saliency-guided-Faster-R-CNN_ACMMM2017. Source code of our ACM MM 2017 paper "Fine-grained Discriminative Localization via Saliency-guided Faster R-CNN"

pspnet-pytorch. PyTorch implementation of PSPNet segmentation network

NTS-Net. This is a PyTorch implementation of the ECCV2018 paper "Learning to Navigate for Fine-grained Classification" (Ze Yang, Tiange Luo, Dong Wang, Zhiqiang Hu, Jun Gao, Liwei Wang).

bilinear-cnn. PyTorch implementation of bilinear CNN for fine-grained image recognition

Deformable-Convolution-V2-PyTorch. Deformable ConvNets V2 (DCNv2) in PyTorch

imgaug. Image augmentation for machine learning experiments.

Super-SloMo. PyTorch implementation of Super SloMo by Jiang et al.

PyTorch_Tutorial. 《Pytorch模型训练实用教程》中配套代码

GHM_Detection. The implementation of “Gradient Harmonized Single-stage Detector” published on AAAI 2019.

RNN-HA. Python

GaitSet. A flexible, effective and fast cross-view gait recognition network

Person-reID-triplet-loss. Person re-ID baseline with triplet loss

FD-GAN. [NeurIPS-2018] FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification.

pytorch-GAN. A minimal implementaion (less than 150 lines of code with visualization) of DCGAN/WGAN in PyTorch with jupyter notebooks

pytorch-book. PyTorch tutorials and fun projects including neural talk, neural style, poem writing, anime generation (《深度学习框架PyTorch：入门与实战》)

triplet-reid-pytorch. A pytorch implementation of the "In Defense of the Triplet Loss for Person Re-Identification" paper (https://arxiv.org/abs/1703.07737). It also contains a implementation of the MGN network from the paper "Learning Discriminative Features with Multiple Granularities for Person Re-Identification". Reaches 83.17% mAP with MGN.

person-reid-triplet-loss-baseline. Rank-1 89% (Single Query) on Market1501 with raw triplet loss, In Defense of the Triplet Loss for Person Re-Identification, using Pytorch

pytorch-TP-GAN. pytorch replicate of TP-GAN "Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis"

TP-GAN. Official TP-GAN Tensorflow implementation for paper "Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis"

WassersteinGAN. Python

simple-faster-rcnn-pytorch. A simplified implemention of Faster R-CNN that replicate performance from origin paper

stargan. StarGAN - Official PyTorch Implementation (CVPR 2018)

transparent_latent_gan. Use supervised learning to illuminate the latent space of GAN for controlled generation and edit

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

PyTorch-GAN. PyTorch implementations of Generative Adversarial Networks.

pytorch-cnn-visualizations. Pytorch implementation of convolutional neural network visualization techniques

Person_reID_baseline_pytorch. :bouncing_ball_person: Pytorch ReID: A tiny, friendly, strong pytorch implement of person re-id / vehicle re-id baseline. Tutorial 👉https://github.com/layumi/Person_reID_baseline_pytorch/tree/master/tutorial

person-reid-incremental. Incremental Learning in Person Re-Identification

deep-person-reid. Torchreid: Deep learning person re-identification in PyTorch.

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

AdversarialNetsPapers. Awesome paper list with code about generative adversarial nets

Generative_Adversarial_Nets. Python

pytorch-tutorial. PyTorch Tutorial for Deep Learning Researchers

nsg. Navigating Spreading-out Graph For Approximate Nearest Neighbor Search

efanna. fast library for ANN search and KNN graph construction

TurtleBotServer. The TurtleBot back-end server for IoT contest

architecture.of.internet-product. 互联网公司技术架构，微信/淘宝/微博/腾讯/阿里/美团点评/百度/OpenAI/Google/Facebook/Amazon/eBay的架构，欢迎PR补充

opencv. Open Source Computer Vision Library

mtcnn-pytorch. Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks

MobileFaceNet_TF. Tensorflow implementation for MobileFaceNet

chainercv. ChainerCV: a Library for Deep Learning in Computer Vision

R3Net. Code for the IJCAI 2018 paper "R^3Net: Recurrent Residual Refinement Network for Saliency Detection"

cupy_windows_wheels.

deform_conv_pytorch. PyTorch Implementation of Deformable Convolution

pytorch-deform-conv. PyTorch implementation of Deformable Convolution

Switchable-Normalization. Code for Switchable Normalization from "Differentiable Learning-to-Normalize via Switchable Normalization", https://arxiv.org/abs/1806.10779

pytorch-faster-rcnn. pytorch1.0 updated. Support cpu test and demo. (Use detectron2, it's a masterpiece)

SENet-PyTorch. Python

insightface. State-of-the-art 2D and 3D Face Analysis Project

py-faster-rcnn. Faster R-CNN (Python implementation) -- see https://github.com/ShaoqingRen/faster_rcnn for the official MATLAB version

face-py-faster-rcnn. Face Detection with the Faster R-CNN

Models.

R2CNN_Faster-RCNN_Tensorflow. Rotational region detection based on Faster-RCNN.

Faster-RCNN_Tensorflow. This is a tensorflow re-implementation of Faster R-CNN: Towards Real-Time ObjectDetection with Region Proposal Networks.

neural-networks-and-deep-learning. Code samples for my book "Neural Networks and Deep Learning"

neural-networks-and-deep-learning. Python