SA-VLM v2: Useful, Comprehensive, and Concise Guidance for Guide-Dog Robots Assisting the Visually Impaired

Woo-han Yun, JaeHo Shin, BeomSu Seo, Jaehong Kim, and ByungOk Han*

* Corresponding author

IEEE International Conference on Robotics & Automation (ICRA), 2026

Selected as an Oral Presentation and Award Finalist

To appear

인간-로봇 공존을 위한 휴머노이드 인공지능 기술 동향

Trends in Humanoid AI Technologies for Human-Robot Coexistence

한병옥, 윤영우, 유영재, 김도형, 조재일, 김재홍

전자통신동향분석, 2025

[Paper]

Replay-Based Scene and Object Augmentation for Real-World Robotic Manipulation

JaeHo Shin, Woo-han Yun, ByungOk Han

Autumn Annual Conference of IEIE, 2025

[Paper]

Space-Aware Instruction Tuning: Dataset and Benchmark for Guide Dog Robots Assisting the Visually Impaired

ByungOk Han*, Woo-han Yun*, Beom-Su Seo, and Jaehong Kim

IEEE International Conference on Robotics & Automation (ICRA), 2025

[Paper][Arxiv][Code]

A Dual Process VLA: Efficient Robotic Manipulation Leveraging VLM

ByungOk Han, Jaehong Kim, and Jinhyeok Jang

Conference on Robot Learning (CoRL) Workshop: LangRob, 2024

[Arxiv]

Rethinking Data Bias: Dataset Copyright Protection via Embedding Class-wise Hidden Bias

Jinhyeok Jang, ByungOk Han, Jaehong Kim, and Chan-Hyun Youn

European Conference on Computer Vision (ECCV), 2024

[Paper]

Learning to Boost Training by Periodic Nowcasting Near Future Weights

Jinhyeok Jang, Woo-han Yun, Won Hwa Kim, Youngwoo Yoon, Jaehong Kim, Jaeyeon Lee, and ByungOk Han

International Conference on Machine Learning (ICML), 2023

[Paper][Code]

Deep Emotion Change Detection via Facial Expression Analysis

ByungOk Han, Cheol-Hwan Yoo, Ho-Won Kim, Jang-Hee Yoo, and Jinhyeok Jang

Neurocomputing, 2023

[Paper][Code]

Simple Yet Effective Approach to Repetitive Behavior Classification based on Siamese Network

Cheol-Hwan Yoo, Jang-Hee Yoo, Ho-Won Kim, and ByungOk Han

International Conference on Pattern Recognition (ICPR), 2022

[Paper]

Target-style-aware Unsupervised Domain Adaptation for Object Detection

Woo-han Yun, ByungOk Han, Jaeyeon Lee, Jaehong Kim, and Junmo Kim

IEEE Robotics and Automation Letters (RA-L) (with ICRA), 2021

[Paper]

Cut-and-Paste Dataset Generation for Balancing Domain Gaps in Object Instance Detection

Woo-Han Yun, Taewoo Kim, Jaeyeon Lee, Jaehong Kim, and Junmo Kim

IEEE Access, 2021

[Paper]

Toward Unbiased Facial Expression Recognition in the Wild via Cross-dataset Adaptation

ByungOk Han, Woo-Han Yun, Jang-Hee Yoo, Won Hwa Kim

IEEE Access, 2020

[Paper][Code]

Automatic Recognition of Children Engagement from Facial Video using Convolutional Neural Networks

Woo-han Yun, Dongjin Lee, Chankyu Park, Jaehong Kim, and Junmo Kim,

IEEE Transactions on Affective Computing, 2020

[Paper]

Head pose estimation using image abstraction and local directional quaternary patterns for multiclass classification

ByungOk Han, Suwon Lee, Hyun S. Yang

Pattern Recognition Letters, 2014

[Paper]

Real-time Visual Target Tracking in RGB-D Data for Person-following Robots

Youngwoo Yoon, Woo-han Yun, Hosub Yoon, Jaehong Kim

International Conference on Pattern Recognition, 2014

[Paper]

Multi-view Facial Expression Recognition Using Parametric Kernel Eigenspace Method Based on Class Features

Woo-han Yun, Dohyung Kim, Chankyu Park, and Jaehong Kim

IEEE International Conference on Systems, Man and Cybernetics, 2013

[Paper]

Visual Object Tracking for Handheld Devices

Woo-han Yun, Dohyung Kim, Jaeyeon Lee, Jaehong Kim

IEEE International Symposium on Industrial Electronics, 2013

[Paper]