avatar

Seil Kang

PhD Student
Yonsei University
seil [at] yonsei [dot] ac [dot] kr

CV | Google Scholar | Github | Linkedin

Short Bio

I am Ph.D. student in Computer Science at Yonsei University.

My research focuses on investigating the behavior and inner workings of large-scale multimodal transformers, with an emphasis on interpretability-driven model improvement and alignment in systems such as Large Vision-Language Models (LVLMs) and Diffusion Transformers (DiTs).

Furthermore, I am also interested in research that analyzes and develops novel user experiences through the latest multimodal transformer science and engineering.

Last Update:

News

Publications [Google Scholar]

  1. Interpretable Motion-Attentive Maps: Spatio-Temporally Localizing Concepts in Video Diffusion Transformers teaser CVPR 2026
    Interpretable Motion-Attentive Maps: Spatio-Temporally Localizing Concepts in Video Diffusion Transformers
    Youngjun Jeon, Seil Kang, Woojung Han, Seong Jae Hwang
    CVPR 2026
    soon

  2. ViKey: Enhancing Temporal Understanding in Videos via Visual Prompting teaser CVPR 2026
    ViKey: Enhancing Temporal Understanding in Videos via Visual Prompting
    Yeonkyung Lee, Dayun Ju, Youngmin Kim, Seil Kang, Seong Jae Hwang
    CVPR 2026
    soon

  3. Rare Text Semantics Were Always There in Your Diffusion Transformer teaser NeurIPS 2025
    Rare Text Semantics Were Always There in Your Diffusion Transformer
    Seil Kang*, Woojung Han*, Dayun Ju, Seong Jae Hwang
    NeurIPS 2025
    pdf

  4. Interpreting Attention Heads for Image-to-Text Information Flow in Large Vision-Language Models teaser NeurIPS 2025 W
    Interpreting Attention Heads for Image-to-Text Information Flow in Large Vision-Language Models
    Jinyeong Kim, Seil Kang, Jiwoo Park, Junhyeok Kim, Seong Jae Hwang
    NeurIPS 2025 Mechanistic Interpretability Workshop (Spotlight, <13%)
    pdf

  5. Neuron-Level Approach for Multi-Hop Reasoning in Large Vision-Language Models teaser Technical Report
    Neuron-Level Approach for Multi-Hop Reasoning in Large Vision-Language Models
    Seil Kang, Jinyeong Kim, Seong Jae Hwang
    Technical Report
    soon

  6. Your Large Vision Language Model Only Needs A Few Attention Heads for Visual Grounding teaser CVPR 2025
    Your Large Vision Language Model Only Needs A Few Attention Heads for Visual Grounding
    Seil Kang, Jinyeong Kim, Junhyeok Kim, Seong Jae Hwang
    CVPR 2025 (Highlight, <3%)
    pdf

  7. See What You Are Told: Visual Attention Sink in Large Multimodal Models teaser ICLR 2025
    See What You Are Told: Visual Attention Sink in Large Multimodal Models
    Seil Kang*, Jinyeong Kim*, Junhyeok Kim, Seong Jae Hwang
    ICLR 2025
    pdf

  8. FALCON: Frequency Adjoint Link with CONtinuous Density Mask for Fast Single Image Dehazing teaser CVPRW 2025
    FALCON: Frequency Adjoint Link with CONtinuous Density Mask for Fast Single Image Dehazing
    Donghyun Kim, Seil Kang, Seong Jae Hwang
    CVPRW 2025
    pdf

  9. WoLF: Wide-scope Large Language Model Framework for CXR Understanding teaser Technical Report
    WoLF: Wide-scope Large Language Model Framework for CXR Understanding
    Seil Kang, Donghyun Kim, Junhyeok Kim, Hyo Kyoung Lee, Seong Jae Hwang
    Technical Report
    pdf

  10. CoBra: Complementary Branch Fusing Class and Semantic Knowledge for Robust Weakly Supervised Semantic Segmentation teaser PR 2024
    CoBra: Complementary Branch Fusing Class and Semantic Knowledge for Robust Weakly Supervised Semantic Segmentation
    Woojung Han, Seil Kang, Kyobin Choo, Seong Jae Hwang
    PR 2024
    pdf