AI open source rankings.
Imitation learning algorithms
[ICLR 2026] UniVideo: Unified Understanding, Generation, and Editing for Videos
A single-header C++ library for simplifying the use of CUDA Runtime Compilation (NVRTC).
Code for "Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulation"
Train and Infer Powerful Sentence Embeddings with AnglE | 🔥 SOTA on STS and MTEB Leaderboard
Meta-SR: A Magnification-Arbitrary Network for Super-Resolution (CVPR2019)
The project is an official implement of our CVPR2018 paper "Deep Back-Projection Networks for Super-Resolution" (Winner of NTIRE2018 and PIRM2018)
Python module for machine learning time series:
Vanilla DQN, Double DQN, and Dueling DQN implemented in PyTorch
VICReg official code base
A large-scale multilingual speech corpus for representation learning, semi-supervised learning and interpretation
Inspiring the Next Generation of Segment Anything Models: Comprehensively Evaluate SAM and SAM 2 with Diverse Prompts Towards Context-Dependent Concepts under Different Scenes
A PyTorch implementation of ESPCN based on CVPR 2016 paper "Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network"
midjourney-proxy的先行版
Implementation of Enformer, Deepmind's attention network for predicting gene expression, in Pytorch
Local-first Apple Health MCP server. Lets AI assistants answer questions about your sleep, workouts, activity and heart data from a local export.
Medical Q&A with Deep Language Models
the framework/ sdk that lets you build browser controlling agents in 3 lines of code. join chat @ https://discord.gg/umgnyQU2K8
Shob – an AI agent that delivers high-quality coding & automation work
Train and block edit and save LoRAs directly inside ComfyUI for Z-image, Flux Klein, SDXL, Flux, WAN 2.2, SD 1.5
[CVPR 2020--Oral] CycleISP: Real Image Restoration via Improved Data Synthesis
A MCP server for Home Assistant
LCNN: End-to-End Wireframe Parsing
Next paradigm for LLM Agent. Unify plan and action through recursive code generation for adaptive, human-like decision-making.
ai challenger 2018细粒度情感分类第一名解决方案, A training framework itegrating tensorflow and pytorch
A tiny lib with pocket-sized implementations of machine learning models in NumPy, most of which will fit in a tweet.
A comprehensive list of awesome document image rectification papers.
Learning Efficient Convolutional Networks through Network Slimming, In ICCV 2017.
Executable GenAI prompt templates
[ICLR 2023 Oral] Image as Set of Points