Beomyoung Kim 김범영
AI Research Engineer — NAVER Cloud (Image Vision)
Computer Vision · Multimodal AI · Vision-Language Models
Summary
I am an AI Research Engineer at NAVER and a Ph.D. student at KAIST, working at the intersection of computer vision and multimodal AI. My research journey began in core visual recognition — semantic and instance segmentation, object detection, and image matting — where I focused on making perception models both accurate and practical through label-efficient (weakly- and semi-supervised) and continual learning. This line of work has produced 13+ publications at top venues including CVPR, ICCV, NeurIPS, ICLR and AAAI (570 citations, h-index 9), with an ICCV 2025 Highlight.
Today, I am extending this deep perception expertise into multimodal & vision-language models — building perception-grounded VLMs and visual reasoning agents that not only recognize what they see, but localize, reason, and act upon it. I am especially driven by research that reaches the real world: throughout my career I have bridged frontier research and large-scale products at NAVER, from a zero-shot image-matting foundation model to generative image editing and face recognition used by millions. My goal is to build AI that perceives, understands, and reasons about the visual world as richly and reliably as people do.
Highlights
- 13+ peer-reviewed papers at CVPR, ICCV, NeurIPS, ICLR, AAAI
- 570 citations, h-index 9 (Google Scholar)
- ICCV 2025 Highlight (top ~3% of accepted papers) — ZIM
- Research → product: image editing & face recognition at NAVER
- 2 papers under review at NeurIPS 2026 & ECCV 2026
- Open-source author of widely-used CV codebases
Experience
AI Research Engineer — NAVER Cloud, Image Vision
Jan 2023 – PresentSeongnam, Korea
- Drive computer-vision research extending into multimodal & vision-language models — building perception-grounded VLMs and visual reasoning agents for fine-grained visual understanding and spatial reasoning.
- Created ZIM, a promptable zero-shot image-matting foundation model (ICCV 2025 Highlight); open-sourced with a public demo and integrated into image-editing experiences.
- Contributed generative image-editing technology presented at TEAM NAVER DAN 24 (CLOVA-X), and face recognition powering NAVER FaceSign.
- First-author publications at top venues; 2 papers currently under review (NeurIPS 2026, ECCV 2026).
AI Research Engineer — NAVER CLOVA, Image Vision
Jan 2021 – Jan 2023Seongnam, Korea
- Advanced label-efficient and continual segmentation, producing first-author CVPR papers: ECLIPSE (continual panoptic segmentation), PointWSSIS (point-supervised instance segmentation), and BESTIE (weakly-supervised instance segmentation).
- Developed weakly- and semi-supervised methods that substantially reduce annotation cost for semantic/instance segmentation; released open-source codebases adopted by the research community.
Research Internships
2018 – 2020- NAVER CLOVA Visual AI (FACE), 2020 — face recognition / understanding research.
- Hyundai Mobis, Autonomous Driving Advanced Development, 2019 — perception for autonomous driving.
- NAVER CLOVA Vision (OCR), 2018 — optical character recognition research.
Education
Ph.D., Kim Jaechul Graduate School of AI — KAIST
MLAI Lab, advised by Prof. Sung Ju Hwang (in parallel with full-time work)
M.S., Electrical Engineering (Future Vehicle) — KAIST
SIIT Lab, advised by Prof. Junmo Kim
B.S., Information and Communication Engineering — Inha University
Under Review
- Under review · NeurIPS 2026A diagnostic framework for 3D spatial reasoning that turns silent perception failures in visual program synthesis into typed diagnoses, driving targeted program repair to rival frontier VLMs without task-specific training.
- Under review · ECCV 2026A segmentation mask-refinement framework that synthesizes realistic, semantic-aware errors via adversarial perturbation and corrects them with contrastive learning, consistently improving state-of-the-art segmentation models.
Selected Publications (★ = first author · full list on Scholar)
- ★ZIM: Zero-Shot Image Matting for Anything. Beomyoung Kim, Chanyong Shin, Joonhyun Jeong, Hyungsik Jung, Se-Yun Lee, Sewhan Chun, Dong-Hyun Hwang, Joonsang Yu. ICCV 2025 Highlight · paper · code · project
- ★Towards Label-Efficient Human Matting: A Simple Baseline for Weakly Semi-Supervised Trimap-Free Human Matting. Beomyoung Kim, Myeong Yeon Yi, Joonsang Yu, Young Joon Yoo, Sung Ju Hwang. arXiv 2024 · paper · code
- ★Rethinking Saliency-Guided Weakly-Supervised Semantic Segmentation. Beomyoung Kim, Donghyeon Kim, Sung Ju Hwang. arXiv 2024 · paper · code
- ★ECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt Tuning. Beomyoung Kim, Joonsang Yu, Sung Ju Hwang. CVPR 2024 · paper · code
- EResFD: Rediscovery of the Effectiveness of Standard Convolution for Lightweight Face Detection. Joonhyun Jeong, Beomyoung Kim, Joonsang Yu, Youngjoon Yoo. WACV 2024 · paper · code
- ★The Devil is in the Points: Weakly Semi-Supervised Instance Segmentation via Point-Guided Mask Representation. Beomyoung Kim, Joonhyun Jeong, Dongyoon Han, Sung Ju Hwang. CVPR 2023 · paper · code
- ★Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinement. Beomyoung Kim, Youngjoon Yoo, Chaeeun Rhee, Junmo Kim. CVPR 2022 · paper · code
- Learning Features with Parameter-Free Layers. Dongyoon Han, Youngjoon Yoo, Beomyoung Kim, Byeongho Heo. ICLR 2022 · paper · code
- ★TricubeNet: 2D Kernel-Based Object Representation for Weakly-Occluded Oriented Object Detection. Beomyoung Kim, Janghyeon Lee, Sihaeng Lee, Doyeon Kim, Junmo Kim. WACV 2022 · paper · code
- ★SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning. Sungmin Cha*, Beomyoung Kim*, Youngjoon Yoo, Taesup Moon (* equal contribution). NeurIPS 2021 · paper · code
- ★Discriminative Region Suppression for Weakly-Supervised Semantic Segmentation. Beomyoung Kim, Sangeun Han, Junmo Kim. AAAI 2021 · paper · code
- ★3D Point Cloud Upsampling and Colorization using GAN. Beomyoung Kim, Sangeun Han, Eojindl Yi, Junmo Kim. MIWAI 2021 · paper
- Fully Automated Valet Parking System Based on Infrastructure Sensing. Hyunjee Ryu, Beomyoung Kim, Heecheol Yoo, Jungwon Lee. RiTA 2020 · paper
Honors & Awards
2025ICCV 2025 Highlight (top ~3% of accepted papers) — ZIM
Academic Service — Reviewer
2026CVPR · ECCV · NeurIPS · ICLR · TPAMI
2025CVPR · ICCV · NeurIPS · ICLR · TMLR
2024CVPR · ECCV · NeurIPS · ICLR · AAAI
2023CVPR · ICCV · NeurIPS · WACV
Invited Talks
2025Centum Digital Week — "Next Code 2025: Beyond AI, Into Agents"
2024TEAM NAVER DAN 24 — CLOVA-X Image Editing
2022Jinhaksa Catch Career-Con — AI Research Engineer career
2022Inha University — Weakly-Supervised Instance Segmentation
2021NeurIPS 2021 Social: ML in Korea — SSUL
Technical Skills
Research areas: Image Segmentation & Detection · Image Matting · Vision Foundation Models · Multimodal / Vision-Language Models · Visual Reasoning Agents · Label-Efficient & Continual Learning
Frameworks & tools: PyTorch · TensorFlow · large-scale / distributed training
Programming: Python · C++ · C · Java
Languages
Korean (native) · English (intermediate — conversational working proficiency)