• 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 (637)
    • 📝 논문리뷰 (627)
      • Computer Vision (403)
      • 3D Vision (134)
      • Audio & Speech (48)
      • NLP (50)
      • RL (15)
      💻 구현 / 프로그래밍 (4) 📒 공부 (2) 🔥 AI소식 (4)

    Recent posts

    [논문리뷰] Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass

    2025년 02월 28일 

    Fast3R 논문 리뷰 (CVPR 2025)

    Tags: 3D Vision, CVPR, DUSt3R, Gaussian Splatting, Meta, Novel View Synthesis, Pose Estimation, ViT

    [논문리뷰] DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation

    2025년 02월 26일 

    DiffSplat 논문 리뷰 (ICLR 2025)

    Tags: 3D Vision, Diffusion, Gaussian Splatting, ICLR, Novel View Synthesis

    [논문리뷰] Continuous 3D Perception Model with Persistent State

    2025년 02월 24일 

    CUT3R 논문 리뷰 (CVPR 2025)

    Tags: 3D Vision, CVPR, DUSt3R, Google, Novel View Synthesis, Pose Estimation, ViT

    [논문리뷰] LM2: Large Memory Models

    2025년 02월 22일 

    LM2 논문 리뷰

    Tags: LLM, NLP, Transformer

    [논문리뷰] Animate Anyone 2: High-Fidelity Character Image Animation with Environment Affordance

    2025년 02월 20일 

    Animate Anyone 2 논문 리뷰

    Tags: Computer Vision, Diffusion

    • Previous
    • 1
    • …
    • 8
    • 9
    • 10
    • 11
    • 12
    • 13
    • 14
    • …
    • 128
    • Next
    • Follow:
    • Feed
    © 2025 kimjy99. Powered by Jekyll & Minimal Mistakes.