Ranked by Attention Score: stars gained over the last 7 complete days
1–100 of 131 by Attention Score · Oct 28, 2026 – Nov 3, 2026 (UTC)
TranslatedChinese version of the AI pose reference gallery · 1439 sets / 2878 images / fully localized into Chinese · zero-dependency static gallery
TranslatedA knowledge graph for mathematics (primary school to high school), English (grade 3 to high school), and junior high school physics: 1,644 knowledge points, 2,403 prerequisite edges, and 6,723 questions, aligned with the curriculum standards, with an adaptive prerequisite diagnostic.
Clone any viral video with AI agents. Not just a script, the whole workflow: swap the face, the words, the B-roll, ship 100 variants in one command, and get your 100M views.
Translated词光 (Ciguang, "word light") · Word Atlas — Illustrated IELTS vocabulary with 7,298 words, UK/US audio and FSRS review. Open-source app + CC BY 4.0 dataset.
An open-source document parsing model with SOTA accuracy and speed, using an RSI loop during post-training.
Specialised AI models for logo design — a brand-analysis model turns a business into constraints, typography and symbol models construct the mark, and a composition engine produces real lockups and clear-space rules. Early access open.
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
WeVisOne-VL is a powerful VLM by the WeChat Vision Team at Tencent, unifying object-level and pixel-level perception from points and boxes to masks and alpha mattes.
The repository host gives no description.
Motion films that never cut to the next slide: every beat grows out of the one before, one continuous camera, continuity measured by an oracle. Product launch films and feature demos, made with a coding agent.
Translated🎬 火宝短剧 (Huobao Short Drama) - An AI-based one-stop short drama generation platform 《Generate a complete short drama from one sentence, fully automated from script to final video》 Huobao Drama - An AI-Powered End-to-End Short Drama Generator "One Sentence to Complete Drama: Fully Automated from Script to Final Video"
TranslatedA skill for making Douyin hit "Vibe knowledge showcase" educational short films: deeply breaks down viral videos, replicates the art style, produces a director's storyboard table, adds sound effects automatically, and outputs the finished video in one click
Translatedaipdd's open-source integrated canvas and agent for short drama production
TranslatedComfyUI Chinese human pose gallery node, supporting multi-view browsing and a Depth Anything → MOSS SFT depth control workflow
Topic in, narrated explainer video out. A Claude Code / Codex skill that turns any topic into a black-canvas motion-graphics explainer video with TTS voiceover, subtitles and a chapter progress bar. Chinese or English; every frame drawn in code with Remotion.
TranslatedMG animation video skill, Douyin viral Vibe knowledge showcase short films, with automatic sound effects and one-click video output. Illustrated explainer video skill — turns an explanation script into an explainer video with "hand-drawn, moving visuals". Graphics are drawn stroke by stroke by code, text is written character by character, and the drawing follows what is being said. Five styles to choose from, rendered in local Chrome, zero image-generation API cost, and any change re-renders within seconds.
Hy-Nomas: Towards Free-form Interactive World Generation
This is the official repo for paper InteractiveWorld A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants
An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
TranslatedHigh-performance · Lightweight · AI Native Video workspace. A video creation workspace for the AI era. On the canvas, freely connect ideas and materials together with the Agent.
A clinical decision-evidence benchmark: pull the one fact an answer rests on, and see whether the assistant's action moves with the evidence. Built on HealthBench.
Open-source studio for video, stills and 3D on your own GPU through ComfyUI
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
Official Hi3D v1.0: high-resolution 3D geometry refinement built on Sparc3D. Inference code, model weights, and documentation.
MatAnyone-E: Sparse Memory Propagation for Efficient High-Resolution Video Matting
Industry leading face manipulation platform
TranslatedFlyingMouse Format (飞鼠格式) - a free file format conversion tool for Windows (works offline, with FFmpeg/LibreOffice/Poppler/Tesseract built in). Converts between image/document/spreadsheet/PPT/PDF/audio-video/WPS formats + OCR + batch conversion; audio supports only common formats. Author: 牢蜂 (LaoFeng, "jailed bee") | For personal free use only; commercial sale, resale, and re-skinning are prohibited
🚀 Truly open-source AI avatar(digital human) toolkit for offline video generation and digital human cloning.
The repository host gives no description.
We propose Prism, a dynamic sparse attention framework for natively training joint video-audio generation models at 2K.
Free offline AI voice studio for Windows — text-to-speech with cloned and built-in voices, and speech recognition with speakers. Russian done right. 100% local, one native .exe, zero Python.
TranslatedIndustry-first professional AI Agent platform for controllable film & video production. From shorts to live-action with Hollywood-standard workflows. (The Chinese part states: the first industrial-grade, full-pipeline AI film and video production platform.)
Free, open-source, local alternative to ElevenLabs and Suno. AI sound effects, music with lyrics, text-to-speech and voice cloning on your own GPU (Stable Audio, ACE-Step and more). No account, no credits, offline. Windows/macOS app, HTTP API and a 21-tool MCP server for Claude Code and Cursor.
Looking Ahead: Modeling Future Evolution in Autoregressive Video Generation
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
The best open-source alternative to Superwhisper & Wispr Flow. Voice-to-text app for macOS with no subscription
AstrBot plugin and local HTTP service for Feiyu TTS, RVC v1 and optional score singing
📊 Cube Core is open-source semantic layer for AI, BI and embedded analytics
NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.
COLMAP - Structure-from-Motion and Multi-View Stereo
[arXiv 2026] Unified Audio-Video Creation via Progressive Training and Asymmetric Scheduling
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
Bring portraits to life!
Distribute and run LLMs with a single file.
Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge
Transformer-SRU LiDAR navigation for Unitree G1: Isaac Lab training, MuJoCo validation, and ROS 2 deployment.
Ongoing research training transformer models at scale
HunyuanVideo: A Systematic Framework For Large Video Generation Model
The repository host gives no description.
The Modular Platform (includes MAX & Mojo)
Reference PyTorch implementation and models for DINOv3
A latent text-to-image diffusion model
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
ncnn is a high-performance neural network inference framework optimized for the mobile platform
Optimized primitives for collective multi-GPU communication
The repository host gives no description.
The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.
The official implementation of 'S4VY: Segment Anything in Feed-Forward 4D Visual Geometry'
An open source implementation of CLIP.
The repository host gives no description.
TranslatedDeepSeek Blue Big Fat Fish Elimination Plan: a Chrome / Edge / Firefox browser extension that identifies and cleans up bot accounts (大肥鱼, Dafeiyu, "big fat fish") driven by the DeepSeek large model and AI agents in Bilibili comment sections. Offline rules + precise judgment by the DeepSeek API, AI comment detection, profile page identification, and one-click clearing by 鲸鱼娘 (Jingyuniang, "whale girl"). DeepSeek AI bot detector for Bilibili comments.
Clone a voice in 5 seconds to generate arbitrary speech in real-time
Point Cloud Library (PCL)
[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
A large collection of system log datasets for AI-driven log analytics [ISSRE'23]
Collection of many countries websites consolidating their main official numbers in easy to read slides
[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer
Code repository for "TrackEverything: Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations"
Image-to-Image Translation in PyTorch
Code for the paper "Language Models are Unsupervised Multitask Learners"
3D Computer Vision Framework
Foundational Models for State-of-the-Art Speech and Text Translation
(⌐■_■) - Deep Reinforcement Learning instrumenting bettercap for WiFi pwning.
Powerful, free, context-aware AI native meeting assistant that transcribes real-time and locally on your computer, writes the minutes, and lets your AI agent drive it.
SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization
Uplift modeling and causal inference with machine learning algorithms
Brian is a free, open source simulator for spiking neural networks.
Instant neural graphics primitives: lightning fast NeRF and more
StyleGAN - Official TensorFlow Implementation
PyTorch3D is FAIR's library of reusable components for deep learning with 3D data
Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages
C-based/Cached/Core Computer Vision Library, A Modern Computer Vision Library
mlpack: a fast, header-only C++ machine learning library
Caffe: a fast open framework for deep learning.
🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP
Hackable and optimized Transformers building blocks, supporting a composable construction.
Real-Time SLAM for Monocular, Stereo and RGB-D Cameras, with Loop Detection and Relocalization Capabilities
Algorithms for outlier, adversarial and drift detection
Hyper-parameter optimization for sklearn
QuadriFlow: A Scalable and Robust Method for Quadrangulation
Vision-Language Pathology Foundation Model - Nature Medicine
ilastik-shell, applets, and workflows to string them together.