Kyoungmin Lee

4 papers · 2025–2026 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (14)

Venues

CVPR (3) AAAI (1)

Top co-authors

Jihun Park (4) Sunghoon Im (4) Jongmin Gim (3) Jaeyeul Kim (3) Wonhyeok Choi (3) Kyumin Hwang (3) Minwoo Choi (2) Seunghun Lee (2) Hyeonseo Jo (1) Minseok Oh (1)

Research topics

Deep Learning (4) Computer Vision (3) Generation · Computer Vision (3) Learning Types (3) Artificial Intelligence (2) Core AI (2) Natural Language Processing (1) Architectures (1) Generation · Natural Language Processing (1) Models (1) Processing (1) Techniques (1)

Keywords

style transfer (2) image generation (1) image editing (1) text-to-image generation (1) singular value decomposition (1) reward function (1) diffusion model (1) autoregressive model (1) style personalization (1) feature decomposition (1) clip embedding (1) cooperative multi-agent reinforcement learning (1) gradient conflict (1) image stylization (1) style consistency (1) multi-task optimization (1) identity consistency (1) text-driven editing (1) style editing (1) object-centric editing (1)

Papers

A Training-Free Style-Personalization via SVD-Based Feature Decomposition CVPR 2026 Infinite-Story: A Training-Free Consistent Text-to-Image Generation AAAI 2026 TaskForce: Cooperative Multi-agent Reinforcement Learning for Multi-task Optimization CVPR 2026 Style-Editor: Text-driven Object-centric Style Editing CVPR 2025