Repository Index

Type a motion, watch a rigged character perform it: fast video model + GVHMR + live Mixamo retargeting

Python package for Bayesian Machine Learning with scikit-learn API

• python
• bayesian-machine-learning
• machine-learning
• scikit-learn

Code for the Nature Scientific Reports paper "Pathologist-level classification of histologic patterns on resected lung adenocarcinoma slides with deep neural networks." A sliding window framework for classification of high resolution whole-slide images, often microscopy or histopathology images.

• histopathology-images
• microscopy
• sliding-windows
• medical-image-analysis

[ICLR 2024] DNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genome

• dataset
• dna
• dna-processing
• dna-training

Kangaroo is an AI-powered SQL client and admin tool for popular databases (MariaDB / MySQL / Oracle / PostgreSQL / Redis / SQLite / SQL Server / ...) on Windows / MacOS / Linux, support table design, query, model, sync, export/import etc, focus on comfortable, fun and developer friendly.

• mysql
• postgresql
• sqlite
• sql

TranslatedVibe Knowledge Showcase (Vibe 知识大赏): one knowledge point → one premium short knowledge video with narration and a cited source for every sentence (Claude Code skill · 44 styles · frame-by-frame video rendered with code)

• chinese
• claude-code
• claude-skills
• explainer-video

WeVisDoc is an end-to-end document parser for page images. Fine-tuned from Qwen3-VL-2B-Instruct and Qwen3-VL-4B-Instruct, it turns a page into structured Markdown, with LaTeX formulas and HTML tables.

Implementation of the Go-ICP algorithm for globally optimal 3D pointset registration

This repository maintains the implementation of "Event-based Stereo Visual Odometry".

A GPU implementation of Convolutional Neural Nets in C++

A ground-up and standalone reimplementation of TensorFlow for ruby. Comes with a pure ruby and OpenCL opcode evaluator

• machine-learning
• tensorflow

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

The repository host gives no description.

Corpus legislativo brasileiro em larga escala e modelo Transformer causal treinado do zero em PyTorch puro.

Stream Data Mining Library for Spark Streaming

Fashion Detection in the Wild (Deep Clothes Detector)

• computer-vision
• deep-learning
• clothes-detection
• clothes-detector

SA-SSD: Structure Aware Single-stage 3D Object Detection from Point Cloud (CVPR 2020)

Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Neural Networks

• caffe
• mtcnn

Implementation of "A Neural Algorithm of Artistic Style" by Tensorflow

RNNLG is an open source benchmark toolkit for Natural Language Generation (NLG) in spoken dialogue system application domains. It is released by Tsung-Hsien (Shawn) Wen from Cambridge Dialogue Systems Group under Apache License 2.0.

• natural-language-processing
• natural-language-generation
• nlg-dataset
• deep-learning

Highly interpretable classifiers for scikit learn, producing easily understood decision rules instead of black box models

Code repository for "TrackEverything: Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations"

• 3d-point-tracking
• point-tracking

Private, unlimited background removal that runs in your browser.