Skip to content
View deep-overflow's full-sized avatar
😎
Focusing
😎
Focusing
29 followers · 53 following
  • CVLAB @ KAIST AI
  • Seoul, Korea
  • 05:06 (UTC +09:00)

Highlights

  • Pro

Block or report deep-overflow

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
deep-overflow/README.md

πŸ‘‹ Hi, I'm Seongchan Kim (κΉ€μ„±μ°¬)

πŸŽ₯ Video Generation & Multimodal Large Language Models (MLLM)
πŸ§‘β€πŸ’» Integrated M.S./Ph.D. @CVLAB in KAIST AI

I design next-generation video generation models and build evaluation frameworks for understanding and improving video diffusion models.
Currently exploring interaction-aware video generation and multimodal understanding of videos.

πŸ§ͺ Research Highlights

  • 🎬 Video Generation & Evaluation β€” Improving interaction fidelity and multi-instance understanding in video diffusion transformers
  • 🧩 Video Object Segmentation (VOS) β€” Multi-granularity & referring VOS with language and temporal reasoning
  • 🧠 MLLM for Video β€” Leveraging multimodal large language models to better understand and describe video content

πŸ“ Publications

  • Self-Evolving Neural Radiance Fields
    Wild3D Workshop @ ICCV 2025
    πŸ”— Project Page

  • MUG-VOS: Multi-Granularity Video Object Segmentation
    AAAI 2025
    πŸ”— Project Page

  • Referring Video Object Segmentation via Language Aligned Track Selection
    arXiv 2025
    πŸ”— Project Page

  • InterRVOS: Interaction-aware Referring Video Object Segmentation
    Under review at AAAI 2026
    πŸ”— Project Page

  • MATRIX: Mask Track Alignment for Interaction-Aware Video Generation
    Under review at ICLR 2026

🌎 Links

✨ β€œUnderstanding the World through Video and Multimodalities.”

Wave

πŸ”„ Last updated: 2025λ…„ 9μ›” 28일 | πŸ’» Made with ❀️ by Deep Overflow

Pinned Loading

  1. SE-NeRF SE-NeRF Public

    Forked from cvlab-kaist/SE-NeRF

    [Wild3D @ ICCVW'25] Official implementation of "SE-NeRF : Self-Evolving Neural Radiance Fields"

    1

  2. MUG-VOS MUG-VOS Public

    Forked from cvlab-kaist/MUG-VOS

    Official Implementation of "Multi-Granularity Video Object Segmentation" (AAAI 2025)

    Python 1

  3. SOLA SOLA Public

    Forked from cvlab-kaist/SOLA

    Official implementation of "Referring Video Object Segmentation via Language Aligned Track Selection".

    Python 1

  4. InterRVOS InterRVOS Public

    Forked from cvlab-kaist/InterRVOS

    Official implementation of "InterRVOS: Interaction-aware Referring Video Object Segmentation".

    Python 1