Graph-based Knowledge Tracing: Modeling Student Proficiency Using Graph Neural Network

Adaptive Model Streaming for real-time video inference on edge devices

LM-Kit Maestro is a secure, innovative desktop application that orchestrates AI agents offline, empowering you to build personalized chatbots with the advanced capabilities of LM-Kit.NET.

[IEEE S&P 22] "LinkTeller: Recovering Private Edges from Graph Neural Networks via Influence Analysis" by Fan Wu, Yunhui Long, Ce Zhang, Bo Li

Enable efficient DNN inference on the edge

LLM chatbot example using OpenVINO with RAG (Retrieval Augmented Generation).

Source code of the paper "Private Collaborative Edge Inference via Over-the-Air Computation".

Lightweight, extensible, and fair multi- DNN manager for heterogeneous embedded devices.

Production Android AI with ExecuTorch 1.0 - Deploy PyTorch models to mobile with NPU acceleration and 50KB footprint

Flutter + LiteRT/tflite demo for obj detection

Code for paper "Dynamic Deep Neural Network Inference via Adaptive Channel Skipping"

Research and training stack for AVA — a tool-using, memory-aware virtual assistant targeting 4 GB VRAM. Spans custom transformers, verifier-RL, external memory, multi-domain benchmarks, and Gemma 4 inference optimization.

This project is a wearable navigation aid that combines computer vision, edge inference, and obstacle detection. The system provides audio feedback to assist visually impaired individuals in navigating their surroundings.

Arbitrary Numbers

Code for Task-Oriented Communication for Multi-Device Cooperative Edge Inference, IEEE TWC, Jan. 2023.

DNN Splitting for Edge Assisted Inference with Convolutional Neural Networks

Computer Vision pipeline for crop and weed detection, with tools for dataset processing, data augmentation, hyperparameter optimization, and NCNN export for edge deployment.

Counting currency from video using RepNet as a base model.