Yuxin Zhang

datatools. Common tools for data processing

RocketKV. [ICML 2025] RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression

KVCache-Factory. Unified KV Cache Compression Methods for Auto-Regressive Models

HELMET. The HELMET Benchmark

MInference. [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which reduces inference latency by up to 10x for pre-filling on an A100 while maintaining accuracy.

RepAdapter. Official implementation of "Towards Efficient Visual Adaption via Structural Re-parameterization".

DoRA. [ICML2024 (Oral)] Official PyTorch implementation of DoRA: Weight-Decomposed Low-Rank Adaptation

Awesome-LLM-Inference. 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉

GaLore. GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

IR-QLoRA. [ICML 2024 Oral] This project is the official implementation of our Accurate LoRA-Finetuning Quantization of LLMs via Information Retention

DiffAgent. [CVPR 2024] DiffAgent: Fast and Accurate Text-to-Image API Selection with Large Language Model

H2O. [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.

laser. The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

streaming-llm. [ICLR 2024] Efficient Streaming Language Models with Attention Sinks

TensorRT-LLM. TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.

DSnoT. Official Pytorch Implementation of Our Paper Accepted at ICLR 2024-- Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs

OWL. Official Pytorch Implementation of "Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity"

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

cutlass. CUDA Templates and Python DSLs for High-Performance Linear Algebra

alpaca-lora. Instruct-tune LLaMA on consumer hardware

MOSS. An open-source tool-augmented conversational language model from Fudan University

wanda. A simple and effective LLM pruning approach.

LLMsNineStoryDemonTower. 【LLMs九层妖塔】分享 LLMs在自然语言处理（ChatGLM、Chinese-LLaMA-Alpaca、小羊驼 Vicuna、LLaMA、GPT4ALL等）、信息检索（langchain）、语言合成、语言识别、多模态等领域（Stable Diffusion、MiniGPT-4、VisualGLM-6B、Ziya-Visual等）等 实战与经验。

ImageBind. ImageBind One Embedding Space to Bind Them All

Unified-Normalization. # Unified Normalization (ACM MM'22) By Qiming Yang, Kai Zhang, Chaoxiang Lan, Zhi Yang, Zheyang Li, Wenming Tan, Jun Xiao, and Shiliang Pu. This repository is the official implementation of "Unified Normalization for Accelerating and Stabilizing Transformers"

LLaMA-Adapter. [ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

lm-evaluation-harness. A framework for few-shot evaluation of language models.

sparsegpt. Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".

CAT. CAT: Collaborative Adversarial Training

peft. 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

LoRA. Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

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

dropit. DropIT: Dropping Intermediate Tensors for Memory-Efficient DNN Training (ICLR 2023)

LATS. To appear in the 11th International Conference on Learning Representations (ICLR 2023).

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

Bi-Mask. Pytorch implementation of our paper accepted by ICML 2023 -- "Bi-directional Masks for Efficient N:M Sparse Training"

SLaK. [ICLR 2023] "More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity"; [ICML 2023] "Are Large Kernels Better Teachers than Transformers for ConvNets?"

deepsparse. Sparsity-aware deep learning inference runtime for CPUs

DDA. Pytorch implementation of our paper accepted by ICLR 2023 -- "Real-time Image Demoireing on Mobile Devices".

LBC. Pytorch implementation of our paper accepted by NeurIPS 2022 -- Learning Best Combination for Efficient N:M Sparsity

MAEPSO. MAEPSO算法

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.

structured_transposable_masks. Code for ICML 2021 submission

CF-ViT. (AAAI 2023 Oral) Pytorch implementation of "CF-ViT: A General Coarse-to-Fine Method for Vision Transformer"

IT-GAN. Python

mae. PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

mtt-distillation. Official code for our CVPR '22 paper "Dataset Distillation by Matching Training Trajectories"

BregmanLearning. Optimizing neural networks via an inverse scale space flow.

constrained_sparsity. Official implementation for the paper "Controlled Sparsity via Constrained Optimization"

EfficientNet-PyTorch. A PyTorch implementation of EfficientNet

Paper-Writing-Tips. MLNLP社区用来帮助大家避免论文投稿小错误的整理仓库。 Paper Writing Tips

Awesome-Dataset-Distillation. A curated list of awesome papers on dataset distillation and related applications.

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

SuperViT. Official Pytorch implementation of Super Vision Transformer (IJCV)

CDP-Towards-Optimal-Filter-Pruning-via-Class-wise-Discriminative-Power. Python

ARM-Net. Pytorch implementation of our paper accepted by ECCV 2022 -- ARM: Any-Time Super-Resolution Method (https://arxiv.org/abs/2203.10812)

Gradient-Rewiring. To appear in the 30th International Joint Conference on Artificial Intelligence (IJCAI 2021).

MopNet. Official Implementation for "Mop Moire Using MopNet" (ICCV 19)

MoirePhotoRestoration-MCNN. This is an unofficial reproduction of paper Moir´e Photo Restoration Using Multiresolution Convolutional Neural Networks.(PyTorch)

MBCNN_torch_demoire. torch18 version, MBCNN demoire,

WDNet_demoire. Wavelet-based and Dual-branch Neural Network for Demoireing ECCV20

White-Box. Pytorch implementation of our paper accepted by IEEE TNNLS, 2022 — Carrying out CNN Channel Pruning in a White Box

1xN. Pytorch implementation of TPAMI 2022 -- 1xN Pattern for Pruning Convolutional Neural Networks

DominoSearch. Python

LCTR. [AAAI 2022] Pytorch implementation of "LCTR: On Awakening the Local Continuity of Transformer for Weakly Supervised Object Localization".

Synaptic-Flow. Jupyter Notebook

GCC. Pytorch implementation of our paper accepted by NeurIPS 2021 -- Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme

convmixer. Implementation of ConvMixer for "Patches Are All You Need? 🤷"

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

PSS-Net. Python

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

ECBSR. Edge-oriented Convolution Block for Real-time Super Resolution on Mobile Devices, ACM Multimedia 2021

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

ICCV2025-Papers-with-Code. ICCV 2025 论文和开源项目合集

convNet.pytorch. ConvNet training using pytorch

CalibTIP. Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming

onnx2X. ONNX2Pytorch

EDSR-PyTorch. PyTorch version of the paper 'Enhanced Deep Residual Networks for Single Image Super-Resolution' (CVPRW 2017)

Pytorch-UNet. PyTorch implementation of the U-Net for image semantic segmentation with high quality images

awesome-vision-language-pretraining-papers. Recent Advances in Vision and Language PreTrained Models (VL-PTMs)

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

PyNET-PyTorch. Generating RGB photos from RAW image files with PyNET (PyTorch)

YOCO-BERT. The official implementation of You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient.

FFSD. Pytorch implementation of our paper accepted by IEEE TNNLS, 2022 -- Distilling a Powerful Student Model via Online Knowledge Distillation

ASRT_SpeechRecognition. A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统

gmm-hmm-asr. Python implementation of simple GMM and HMM models for isolated digit recognition.

dnn-hmm-asr. Hybrid DNN-HMM model for isolated digit recognition

academicpages.github.io. Github Pages template based upon HTML and Markdown for personal, portfolio-based websites.

APoT_Quantization. PyTorch implementation for the APoT quantization (ICLR 2020)

VPC-Net. The codes for ISPRS Journal paper 'VPC-Net: Completion of 3D Vehicles from MLS Point Clouds'

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

lottery-jackpots. Pytorch implementation of our paper accepted by TPAMI 2023 — Lottery Jackpots Exist in Pre-trained Models

tvm_mlir_learn. compiler learning resources collect.

SMSR. [CVPR 2021] Exploring Sparsity in Image Super-Resolution for Efficient Inference

tvm. Open Machine Learning Compiler Framework

torchmetrics. Machine learning metrics for distributed, scalable PyTorch applications.

mobilenetv3.pytorch. 74.3% MobileNetV3-Large and 67.2% MobileNetV3-Small model on ImageNet

GraSP. Code for "Picking Winning Tickets Before Training by Preserving Gradient Flow" https://openreview.net/pdf?id=SkgsACVKPH

rigl-torch. Lightweight torch implementation of rigl, a sparse-to-sparse optimizer.

PAMS. PArameterized Max Scale

SiMaN. Pytorch implementation of our paper accepted by TPAMI 2022 -- SiMaN: Sign-to-Magnitude Network Binarization

apex. A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

NM-sparsity. Python

EPruner. Pytorch implementation of our paper accepted by IEEE TNNLS, 2021 -- Network Pruning using Adaptive Exemplar Filters

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

RepVGG. RepVGG: Making VGG-style ConvNets Great Again

ml-visuals. 🎨 ML Visuals contains figures and templates which you can reuse and customize to improve your scientific writing.

ICLR2021-OpenReviewData. Crawl & visualize ICLR papers and reviews.

xmu-thesis-grd. 厦门大学研究生学位论文 LaTeX 模板

blocksparse. Efficient GPU kernels for block-sparse matrix multiplication and convolution

DeepLearningExamples. State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.

DMAD. Pytorch implementation of our paper accepted by IEEE TMM, 2022 --Learning Efficient GANs for Image Translation via Differentiable Masks and co-Attention Distillation

mobileNet-v2_cifar10. a pytorch implement of mobileNet v2 on cifar10

Advanced-Deep-Learning-with-Keras. Advanced Deep Learning with Keras, published by Packt

pytorch-gradual-warmup-lr. Gradually-Warmup Learning Rate Scheduler for PyTorch

google-research. Google Research

Robustness-Aware-Pruning-ADMM. Code release for "Adversarial Robustness vs Model Compression, or Both?"

lookahead_pruning. Lookahead: A Far-sighted Alternative of Magnitude-based Pruning (ICLR 2020)

Pruning-Filter-in-Filter. Pruning Filter in Filter(NeurIPS2020)

STR. Soft Threshold Weight Reparameterization for Learnable Sparsity

sparse-evolutionary-artificial-neural-networks. Always sparse. Never dense. But never say never. A Sparse Training repository for the Adaptive Sparse Connectivity concept and its algorithmic instantiation, i.e. Sparse Evolutionary Training, to boost Deep Learning scalability on various aspects (e.g. memory and computational time efficiency, representation and generalization power).

taichi. Productive, portable, and performant GPU programming in Python.

pytorch_block_sparse. Fast Block Sparse Matrices for Pytorch

MEAL-V2. MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks. In NeurIPS 2020 workshop.

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.

RBNN. Pytorch implementation of our paper accepted by NeurIPS 2020 -- Rotated Binary Neural Network

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

cnnvisualizer. Visualizer for Deep Neural Networks

awesome-compression-papers. Paper collection about model compression and acceleration: Pruning, Quantization, Knowledge Distillation, Low Rank Factorization, etc

mindspore. MindSpore is a new open source deep learning training/inference framework that could be used for mobile, edge and cloud scenarios.

ResRep. ResRep: Lossless CNN Pruning via Decoupling Remembering and Forgetting (ICCV 2021)

EagleEye. (ECCV'2020 Oral)EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning

ECCV2026-Papers-with-Code. ECCV 2026 论文和开源项目合集，同时欢迎各位大佬提交issue，分享ECCV 2026论文和开源项目

YOLOv3v4-ModelCompression-MultidatasetTraining-Multibackbone. YOLO ModelCompression MultidatasetTraining

pytorch_stacked_hourglass. Pytorch implementation of the ECCV 2016 paper "Stacked Hourglass Networks for Human Pose Estimation"

Efficient-Deep-Learning. Collection of recent methods on (deep) neural network compression and acceleration.

torchsummaryX. torchsummaryX: Improved visualization tool of torchsummary

TNN. TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is distinguished by several outstanding features, including its cross-platform capability, high performance, model compression and code pruning. Based on ncnn and Rapidnet, TNN further strengthens the support and performance optimization for mobile devices, and also draws on the advantages of good extensibility and high performance from existed open source efforts. TNN has been deployed in multiple Apps from Tencent, such as Mobile QQ, Weishi, Pitu, etc. Contributions are welcome to work in collaborative with us and make TNN a better framework.

dmcp. Python

HRank. Pytorch implementation of our CVPR 2020 (Oral) -- HRank: Filter Pruning using High-Rank Feature Map

yolov3. Ultralytics YOLOv3 in PyTorch > ONNX > CoreML > TFLite

awesome-AutoML. Curating a list of AutoML-related research, tools, projects and other resources

Fast-Vital. Speed up vital tracker using pruning or quantification method

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

Awesome-AutoDL. Automated Deep Learning: Neural Architecture Search Is Not the End (a curated list of AutoDL resources and an in-depth analysis)

AutoDL-Projects. Automated deep learning algorithms implemented in PyTorch.

HRank. Pytorch implementation of our paper accepted by CVPR 2020 (Oral) -- HRank: Filter Pruning using High-Rank Feature Map

attention-is-all-you-need-pytorch. A PyTorch implementation of the Transformer model in "Attention is All You Need".

BERT-related-papers. BERT-related papers

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

MobileNetV2_Pytorch. This Pytorch Version of MobileNetV2 is converted from my Caffe Version

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

toolkit-legacy. Visual Object Tracking (VOT) challenge evaluation toolkit

GSM-SGD. Global Sparse Momentum SGD for pruning very deep neural networks

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

faster_rcnn_pytorch. Faster RCNN with PyTorch

models. Models and examples built with TensorFlow

tensorflow. An Open Source Machine Learning Framework for Everyone

pytorch-mobilenet-v2. A PyTorch implementation of MobileNet V2 architecture and pretrained model.

Compression_Paper.

pytorch-cifar. 95.47% on CIFAR10 with PyTorch

MABN. Python

ABCPruner. Pytorch implementation of our paper accepted by IJCAI 2020 -- Channel Pruning via Automatic Structure Search

FilterSketch. Pytorch implementation of our paper accepted by IEEE TNNLS, 2021 -- Filter Sketch for Network Pruning

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

BERT-pytorch. Google AI 2018 BERT pytorch implementation

DALI. A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

vision. Datasets, Transforms and Models specific to Computer Vision

ImageNet. This implements training of popular model architectures, such as AlexNet, ResNet and VGG on the ImageNet dataset(Now we supported alexnet, vgg, resnet, squeezenet, densenet)

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

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

Tutorial_BayesianCompressionForDL. A tutorial on "Bayesian Compression for Deep Learning" published at NIPS (2017).

pytorch_DoReFaNet. A pytorch implementation of DoReFa-Net

PyMDNet. MDNet PyTorch implementation

Vital_release. VITAL: VIsual Tracking via Adversarial Learning

py-Vital. Vital tracker implemented using PyTorch

BinaryNet.pytorch. Binarized Neural Network (BNN) for pytorch

XNOR-Net-PyTorch. PyTorch Implementation of XNOR-Net

YOLO_v3_tutorial_from_scratch. Accompanying code for Paperspace tutorial series "How to Implement YOLO v3 Object Detector from Scratch"

pytorch_workplace. Random miniprojects with pytorch.

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

SiamFC-PyTorch. SiamFC PyTorch

Towards-Realtime-MOT. Joint Detection and Embedding for fast multi-object tracking

Deep-Learning-with-PyTorch-Tutorials. 深度学习与PyTorch入门实战视频教程 配套源代码和PPT

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

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]

nndl. 邱锡鹏《神经网络与深度学习》（蒲公英书）理论书 v2 与通识版