• 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 (661)
    • 📝 논문리뷰 (641)
      • Computer Vision (406)
      • 3D Vision (141)
      • NLP (54)
      • Audio & Speech (48)
      • RL (18)
      💻 구현 / 프로그래밍 (4) 📒 공부 (2) 🎮 GAME (14)

    Recent posts

    [논문리뷰] TTRL: Test-Time Reinforcement Learning

    2025년 06월 20일 

    TTRL 논문 리뷰

    Tags: LLM, NLP, Reinforcement Learning

    [논문리뷰] Align3R: Aligned Monocular Depth Estimation for Dynamic Videos

    2025년 06월 18일 

    Align3R 논문 리뷰 (CVPR 2025)

    Tags: 3D Vision, CVPR, DUSt3R, Monocular Depth Estimation

    [논문리뷰] Truncated Consistency Models

    2025년 06월 16일 

    TCM 논문 리뷰 (ICLR 2025)

    Tags: Computer Vision, Diffusion, ICLR, Image Generation, NVIDIA

    [논문리뷰] Generating Physically Stable and Buildable LEGO Designs from Text

    2025년 06월 14일 

    LegoGPT 논문 리뷰 (CVPR 2024 Highlight)

    Tags: 3D Vision, Autoregressive, CVPR, Transformer

    [논문리뷰] LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale

    2025년 06월 12일 

    LiveCC 논문 리뷰 (CVPR 2025)

    Tags: Computer Vision, CVPR, Diffusion

    • Previous
    • 1
    • 2
    • 3
    • 4
    • 5
    • 6
    • …
    • 133
    • Next
    • Follow:
    • Feed
    © 2025 kimjy99. Powered by Jekyll & Minimal Mistakes.