• 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 (682)
    • 📝 논문리뷰 (660)
      • Computer Vision (414)
      • 3D Vision (148)
      • NLP (57)
      • Audio & Speech (48)
      • RL (20)
      💻 구현 / 프로그래밍 (4) 📒 공부 (2) 🎮 GAME (16)

    Recent posts

    [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

    [논문리뷰] Diffusion Models Are Real-Time Game Engines

    2025년 04월 17일 

    GameNGen 논문 리뷰 (ICLR 2025)

    Tags: Computer Vision, Diffusion, Google, ICLR, Reinforcement Learning

    [논문리뷰] LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation Models

    2025년 04월 15일 

    LoRA3D 논문 리뷰 (ICLR 2025 Spotlight)

    Tags: 3D Vision, DUSt3R, ICLR, LoRA, Novel View Synthesis, NVIDIA, Pose Estimation

    [논문리뷰] L4P: Low-Level 4D Vision Perception Unified

    2025년 04월 13일 

    L4P 논문 리뷰

    Tags: Computer Vision, Monocular Depth Estimation, NVIDIA

    • Previous
    • 1
    • …
    • 11
    • 12
    • 13
    • 14
    • 15
    • 16
    • 17
    • …
    • 137
    • Next
    • Follow:
    • Feed
    © 2025 kimjy99. Powered by Jekyll & Minimal Mistakes.