• Skip to primary navigation
  • Skip to content
  • Skip to footer
전생했더니 인공지능이었던 건에 대하여
  • Tags

    JiYeop Kim

    Diffusion은 신이고 GPT는 무적이다

    • Seoul, Korea
    • GitHub
    • Email
    • 📂 전체 게시글 (818)
    • 📝 논문리뷰 (769)
      • Computer Vision (462)
      • 3D Vision (201)
      • NLP (62)
      • Audio & Speech (48)
      • RL (27)
      💻 구현 / 프로그래밍 (4) 📒 공부 (2) 🎮 GAME (43)

    Recent posts

    [논문리뷰] LumiGauss: Relightable Gaussian Splatting in the Wild

    2025년 03월 22일 

    LumiGauss 논문 리뷰 (WACV 2025)

    Tags: 3D Vision, Gaussian Splatting, Microsoft, Novel View Synthesis

    [논문리뷰] Improved Distribution Matching Distillation for Fast Image Synthesis

    2024년 03월 20일 

    DMD2 논문 리뷰 (NeurIPS 2024 Oral)

    Tags: Computer Vision, Diffusion, Distillation, NeurIPS, Text-to-Image

    [논문리뷰] From Slow Bidirectional to Fast Autoregressive Video Diffusion Models

    2025년 03월 18일 

    CausVid 논문 리뷰 (CVPR 2025)

    Tags: Computer Vision, CVPR, Diffusion, Distillation, DiT, Text-to-Video

    [논문리뷰] Show-o: One Single Transformer to Unify Multimodal Understanding and Generation

    2025년 03월 16일 

    Show-o 논문 리뷰 (ICLR 2025)

    Tags: Computer Vision, ICLR, LLM, Text-to-Image, Transformer

    [논문리뷰] T-Stitch: Accelerating Sampling in Pre-trained Diffusion Models with Trajectory Stitching

    2025년 03월 14일 

    T-Stitch 논문 리뷰 (ICLR 2025)

    Tags: Computer Vision, Diffusion, ICLR, NVIDIA, Text-to-Image

    • Previous
    • 1
    • …
    • 41
    • 42
    • 43
    • 44
    • 45
    • 46
    • 47
    • …
    • 164
    • Next
    • Follow:
    • Feed
    © 2026 kimjy99. Powered by Jekyll & Minimal Mistakes.