Repository Index

Robust Speech Recognition via Large-Scale Weak Supervision

NSFW detection on the client-side via TensorFlow.js

• machine-learning
• machinelearning
• javascript
• tensorflowjs

Interactive Image Generation via Generative Adversarial Networks

• generative-adversarial-network
• image-manipulation
• computer-graphics
• computer-vision

OCR in Javascript via Emscripten

Generation of protein sequences and evolutionary alignments via discrete diffusion models

• discrete-diffusion
• generative-model
• multiple-sequence-alignment
• protein-sequences

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

• 3d-point-tracking
• point-tracking

Laya typed decisions on Linux x86_64 via ONNX Runtime

Fusing Histology and Genomics via Deep Learning - IEEE TMI

• pathomic
• fusion
• multimodal
• pathology

Official repository for the paper “RSIPO: Recursive Self-Improving Policy Optimization for Agentic Reinforcement Learning via Skill-Policy Co-Evolution”

[arXiv 2026] Unified Audio-Video Creation via Progressive Training and Asymmetric Scheduling

• audio-to-video
• joint-audio-video-generation
• unified-model
• video-to-audio

TSPS is a cross platform Toolkit for Sensing People in Spaces. It performs openCV operations on live video (Kinect, web camera, etc) and sends it to clients as JSON (via WebSockets), OSC, TUIO, or TCP.

[ACL 2025] The official implementation of the paper "PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free".

A multilayer perceptron network implemented in Go, with training via backpropagation.

Push-to-talk voice dictation for Linux. 100% local, multilingual (25+ languages), with speaker diarization. Qt frontend, Rust backend on NVIDIA Parakeet via ONNX Runtime. KDE Plasmoid integrated.

• asr
• linux
• nvidia
• parakeet

Reducing Bias in Modeling Real-world Password Strength via Deep Learning and Dynamic Dictionaries

Open-source real-time Voice AI infrastructure in Go. Stream audio via WebRTC or WebSocket, connect STT → LLM → TTS pipelines, and build scalable voice agents and conversational AI applications.

• audio-streaming
• conversational-ai
• generative-ai
• llm

Demo of high performance AI model (pmml export) evaluator api base on Vert.x, Supports dynamic routing configuration for multiple pmml models via JSON

• pmml
• ai
• java-pmml
• verticle

Estimating the number of clusters in a data set via the gap statistic. Implemented in H2O-3

• kmeans
• kmeans-clustering
• clustering
• gap-statistic