Author

Sohyun Lee

h-index 6 View on Semantic Scholar

We have 2 of 12 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Open access Jul 2026

Global-to-Local Visual Conditioning for Image Captioning with a Frozen Vision–Language Model

This study investigates an input-level visual conditioning approach for image captioning using a frozen ResNet-50 image encoder and a frozen Phi-3 Mini language model, providing an empirical analysis of global and local visual conditioning for parameter-efficient caption generation with frozen pretrained components.

Sohyun Lee, Dae-Nyoung Heo · Applied Sciences · 0 citations

#artificial intelligence Preprint Apr 2025

TestDG: Test-time Domain Generalization for Continual Test-time Adaptation

A novel online test-time domain generalization framework for CTTA, dubbed TestDG, which aims to learn features invariant to both current and previous test domains on the fly during testing, improving the potential for effective generalization to future domains.

Sohyun Lee, Nayeong Kim, Juwon Kang et al. · 0 citations