Project

Techniques:

• On-Device Training (related to my CVPR 2026 publication on CPS-Prompt)
• Online Continual Learning (related to MixER, IEEE Access 2024)
• Hardware-Aware Neural Architecture Search (related to GTSNet, EAAI 2023)
• Multimodal Learning and Out-of-Distribution Detection (related to MAND, EIML @ ICML 2026)

Code:

• github.com/laymond1/cps-prompt
• github.com/laymond1/MixER
• github.com/jgpark92/GTSNet

Techniques: Variational Autoencoder (VAE), Bayesian Optimization, Latent Space Analysis

Materials:

• Slides
• Code: github.com/sunghwanism/NewMoses

Techniques: Vision-Language Model, Cross-Modal Learning, Sentiment Analysis

Materials:

• Slides

Techniques: YOLO, Hardware-Aware NAS, Post-Training Quantization, Docker

Code & Resources:

• github.com/ML-TANGO/TANGO
• TANGO Community Conference: TANGO/AutoNN

Techniques: Polyp Segmentation, Medical Image Analysis

Techniques:

• Hardware-Aware Neural Architecture Search (related to LUT-NAS, IEEE Access 2023, and group-structure NAS, Electronics Letters 2022)
• Real-time Human Activity Recognition (related to LUT-NAS and MTS-Module, IEEE Access 2022)
• Multi-scale Temporal Sampling (related to MTS-Module)

Code:

• github.com/laymond1/HAR-Model-Latency
• github.com/minercode625/grunas
• github.com/jgpark92/MTS-ConvNet

Techniques: Orbit Segmentation, 3D Image Classification

Related Paper: Neural Network-based Method for Diagnosing Graves’ Orbitopathy Using Orbital Computed Tomography (Scientific Reports, 2022)

Code:

• github.com/laymond1/Graves-Orbitopathy-Diagnosis-using-Neural-Network