Nexa SDK is a comprehensive toolkit for supporting GGUF and MLX model formats. It supports LLM and VLMs
Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement (NeurIPS 2020)
This repository contains notebooks that show the usage of TensorFlow Lite for quantizing deep neural networks.
A custom RAG pipeline for multi-document QA from PDF/DOCX documents, in Android
This is a web demo for camera-based PPG sensing (rPPG).
Embeddings from sentence-transformers in Android! Supports all-MiniLM-L6-V2, bge-small-en, snowflake-arctic, model2vec models and more
An Android app running inference on Depth-Anything and Depth-Anything-V2
Object detection inference with Roboflow Train models on NVIDIA Jetson devices.
[NeurIPS'24] DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators
Approach to implementing distributed training of an ML model: server/device training for iOS.
On-Device Static Sentence Embeddings in Swift/iOS/macOS apps
Control your computer using hand gestures with AI, using Google's MediaPipe and OAK-D Lite camera.
End-to-end on-device federated learning, "An On-Device Federated Learning System for SMS Spam Classification", IEEE MIT URTC 2022
SponsorMe is a project to help provide access to digital tools for learning, powered by on-device machine learning, innovation and willingness, to those people that have limited access to technology due to demographics, disabilities, economy or other multiple reasons.
A minimalistic Android app showcasing semantic search using ObjectBox and Lucene KNN, leveraging the MiniLM-L6-V2 embedding model and bert_vocab.txt for efficient retrieval.
Mindful Coffee ☕️ – Smartly track caffeine intake, visualize its decay, predict sleep impact & get reminders. Built with SwiftUI, SwiftData, HealthKit & on-device machine learning.
An Android app where users draw a number and machine learning does the rest
Python ML library for person fall detection. Intended for IoT deployments with on-device inference and on-device transfer learning.
As described in "Towards Full On-Tiny-Device Learning: Guided Search for a Randomly Initialized Neural Network"
Add a description, image, and links to the on-device-ml topic page so that developers can more easily learn about it.
To associate your repository with the on-device-ml topic, visit your repo's landing page and select "manage topics."