Seil Kang

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 · Bronze 🗺️ Taxonomy Completionist (11)

Venues

CVPR (3) ICLR (1)

Top co-authors

Seong Jae Hwang (4) Junhyeok Kim (2) Jinyeong Kim (2) Youngmin Kim (1) Yeonkyung Lee (1) Dayun Ju (1) Youngjun Jun (1) Woojung Han (1)

Research topics

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

Keywords

attention mechanism (2) temporal reasoning (1) multimodal learning (1) visual grounding (1) object localization (1) visual attention (1) saliency map (1) frame selection (1) large multimodal model (1) vision-language model (1) large vision-language model (1) transformer decoder (1) visual prompting (1) training-free method (1) visual hallucination (1) video semantic segmentation (1) video large language model (1) video diffusion transformer (1) motion localization (1) motion concept (1)

Papers

I'm a Map! Interpretable Motion-Attentive Maps: Spatio-Temporally Localizing Concepts in Video Diffusion Transformers CVPR 2026 ViKey: Enhancing Temporal Understanding in Videos via Visual Prompting CVPR 2026 See What You Are Told: Visual Attention Sink in Large Multimodal Models ICLR 2025 Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding CVPR 2025