Profile

Hi I’m Youyang. I am an experienced industrial researcher specializing in Computer Vision, Natural Language Processing, and Machine Learning, with track record in patents, publications, and practical implementations.

Currently, I lead a research team at Kioxia Corporation, Japan, focusing on basic and applied studies in Computer Vision, Natural Language Processing, Machine Learning, and Memory Systems. My research interests lie in the intersection of memory, intelligence, and alignment in vision and language models.

I have co-authored over 30 patents and research articles, including publications in notable venues such as ECCV, ACCV and EMNLP. Additionally, I have served as a reviewer for venues including ACL Rolling Review, ICCV, WACV, ACL, EMNLP and NAACL. I have received outstanding reviewer recognition at EMNLP. I am also a Senior Member of IEEE. With over 14 years of industrial R&D experiences, I previously worked at Toshiba Corporation and hold a B.Eng from Universiti Malaya, Malaysia. The tools I help develop inspect and analyze millions of visual data daily in social infrastructure & semiconductor industries. I speak English, Japanese, Chinese and Malay.

Google Scholar LinkedIn Publications List

Selected Works

Aligning Human-AI Perception in Vision Foundation Models

Prompt-Guided Attention Head Selection for Focus-Oriented Image Retrieval
Yuji Nozawa, Yu-Chieh Lin, Kazumoto Nakamura, Youyang Ng
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2025 (paper)

Improving Image Clustering with Artifacts Attenuation via Inference-Time Attention Engineering
Kazumoto Nakamura, Yuji Nozawa, Yu-Chieh Lin, Kengo Nakata, Youyang Ng
Asian Conference on Computer Vision (ACCV), 2024 (paper)

Revisiting Relevance Feedback for CLIP-based Interactive Image Retrieval
Ryoya Nara, Yu-Chieh Lin, Yuji Nozawa, Youyang Ng, Goh Itoh, Osamu Torii, Yusuke Matsui
European Conference on Computer Vision (ECCV) Workshops, 2024 (paper, blog)

Rethinking Vision Models with Separable, Explainable & Editable Knowledge

Revisiting a kNN-based Image Classification System with High-capacity Storage
Kengo Nakata, Youyang Ng, Daisuke Miyashita, Asuka Maki, Yu-Chieh Lin, Jun Deguchi
European Conference on Computer Vision (ECCV), 2022, Oral Acceptance - Top 2.7% (paper, press, blog)

Rethinking Sparse Lexical Representations for Image Retrieval in the Age of Rising Multi-Modal Large Language Models
Kengo Nakata, Daisuke Miyashita, Youyang Ng, Yasuto Hoshi, Jun Deguchi
European Conference on Computer Vision (ECCV) Workshops, 2024 (paper, blog)

Language Models with Retrieval-Augmented & Retrieval-Centric Generation

RaLLe: A Framework for Developing and Evaluating Retrieval-Augmented Large Language Models
Yasuto Hoshi, Daisuke Miyashita, Youyang Ng, Kento Tatsuno, Yasuhiro Morioka, Osamu Torii, Jun Deguchi
Conference on Empirical Methods in Natural Language Processing (EMNLP) System Demonstrations, 2023 (paper, code, blog)

SimplyRetrieve: A Private and Lightweight Retrieval-Centric Generative AI Tool
Youyang Ng, Daisuke Miyashita, Yasuto Hoshi, Yasuhiro Morioka, Osamu Torii, Tomoya Kodama, Jun Deguchi
arXiv, 2023 (paper, code, blog)