AwesomeRepos
Sign in

Tags / Machine learning /

Paper implementation

Code that implements the model or method of one specific research paper.

Repositories

79

Net stars gained, last 7 days

+4,748

Top-level Tag

Machine learning

Net stars gained each day, last 90 days

2026-10-22: +1,222 net stars. Most from zita-ch/supermimic_vibed, +227.2026-10-23: +970 net stars. Most from hi3d-official/Hi3Dv1.0, +144.2026-10-28: +741 net stars. Most from yifanzhang-pro/recurrent-looped-tranformer, +148.2026-10-29: +1,021 net stars. Most from MUSE-AI-Lab/ReMCTS, +184.2026-10-31: +772 net stars. Most from hyz317/HairDeck, +390.

Peak days

  1. 1

    Oct 22, 2026 +1,222 net stars (median day +209)

  2. 2

    Oct 23, 2026 +970 net stars (median day +209)

  3. 3

    Oct 28, 2026 +741 net stars (median day +209)

  4. 4

    Oct 29, 2026 +1,021 net stars (median day +209)

  5. 5

    Oct 31, 2026 +772 net stars (median day +209)

A peak day has at least 2 times the net stars of the median day of this chart, and at least 100 more. For each peak day, the list shows the repositories that gained the most net stars that day. It also shows their GitHub releases of that day or the day before (UTC), and their creation date when it was 14 days or less before. These events occur near the same day. They do not show why the stars came.

Largest

Most stars in total now.

  1. labmlai/annotated_deep_learning_paper_implementations68K

    readme: This is a collection of simple PyTorch implementations of neural networks and related algorithms.

  2. CorentinJ/Real-Time-Voice-Cloning60K

    readme: This repository is an implementation of Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis (SV2TTS)

  3. google-research/bertarchived · 40K

    description: TensorFlow code and pre-trained models for BERT

  4. TencentARC/GFPGAN38K

    readme: GFP-GAN: Towards Real-World Blind Face Restoration with Generative Facial Prior

  5. XingangPan/DragGAN36K

    description: Official Code for DragGAN (SIGGRAPH 2023)

  6. lllyasviel/ControlNet34K

    readme: Official implementation of Adding Conditional Control to Text-to-Image Diffusion Models.

  7. chenfei-wu/TaskMatrix34K

    readme: See our paper: Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models

  8. karpathy/llm.c31K

    readme: The best introduction to the llm.c repo today is reproducing the GPT-2 (124M) model.

  9. huggingface/open-r126K

    readme: We will use the DeepSeek-R1 tech report as a guide, which can roughly be broken down into three main steps:

  10. Vision-CAIR/MiniGPT-426K

    description: Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

Newest Admissions

Entered the index by the rising rule, newest first.

  1. hyz317/HairDeck778

    description: HairDeck: Animation-Ready Stylized Hair Cards from a Single Image

  2. inclusionAI/IDM235

    description: Official code for Intrinsic Distribution Matching (IDM).

  3. MUSE-AI-Lab/ReMCTS274

    readme: ReMCTS: Reflection-Enhanced Monte Carlo Tree Search for Code Generation

  4. MUSE-AI-Lab/Concept-Brittleness262

    readme: Interpreting Object-Dependent Concept Brittleness in Text-to-Image Diffusion Models

  5. facebookresearch/InteractiveWorld214

    description: This is the official repo for paper InteractiveWorld A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants

  6. KooroshRH/AReA157

    description: Official implementation of "AReA: Adaptive Receptive-Field Attention for Efficient High-Resolution Diffusion Transformers"

  7. shengshu-ai/Motus2290

    readme: We present **Motus2**, a self-evolving general world model for dexterous manipulation.

  8. lee-dro/PatchCore216

    readme: 复现 PatchCore 的记忆库、近邻搜索和异常图生成流程

  9. yifanzhang-pro/recurrent-looped-tranformer1.1K

    description: Official Project Page for Recurrent Looped Transformer (RLT) (https://arxiv.org/abs/2610.07591)

  10. jrryzh/F2G-Pose129

    description: This repo is the official implementation of "F2G-Pose: Geometry-Aware Foundation Feature Lifting for Direct RGB-D Category-Level Object Pose Estimation".

All 79 in the Repository Index

How a repository gets this Tag

An agent reads the description, the GitHub topics, and the start of the README of each repository. It chooses Tags only from the Tag list in the AwesomeRepos source code. For each Tag, it quotes the text. A code check keeps the Tag only when the quote is in that text. The quote under each repository is that evidence. A Tag does not rank repositories. It does not say that one repository can replace another. To report a wrong Tag, use "Report a problem with this page" on the page of the repository. All numbers on this page count only visible repositories.