• 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 (626)
    • 📝 논문리뷰 (616)
      • Computer Vision (401)
      • 3D Vision (126)
      • Audio & Speech (48)
      • NLP (49)
      • RL (15)
      💻 구현 / 프로그래밍 (4) 📒 공부 (2) 🔥 AI소식 (4)

    Recent posts

    [논문리뷰] One Step Diffusion via Shortcut Models

    2025년 04월 27일 

    Shortcut Model 논문 리뷰 (ICLR 2025 Oral)

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

    [논문리뷰] Restructuring Vector Quantization with the Rotation Trick

    2025년 04월 25일 

    Rotation Trick 논문 리뷰 (ICLR 2025)

    Tags: Computer Vision, Google, ICLR, Vector Quantization

    [논문리뷰] Vision Language Models are In-Context Value Learners

    2025년 04월 23일 

    GVL 논문 리뷰 (ICLR 2025 Spotlight)

    Tags: Computer Vision, Google, ICLR, Reinforcement Learning

    [논문리뷰] No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images

    2025년 04월 21일 

    NoPoSplat 논문 리뷰 (ICLR 2025 Oral)

    Tags: 3D Vision, DUSt3R, Gaussian Splatting, ICLR, Microsoft, Novel View Synthesis, NVIDIA, ViT

    [논문리뷰] VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation

    2025년 04월 19일 

    VILA-U 논문 리뷰 (ICLR 2025)

    Tags: Computer Vision, Contrastive Learning, ICLR, Image Classification, NVIDIA, Text-to-Image, Text-to-Video

    • Previous
    • 1
    • 2
    • 3
    • 4
    • 5
    • 6
    • …
    • 126
    • Next
    • Follow:
    • Feed
    © 2025 kimjy99. Powered by Jekyll & Minimal Mistakes.