JiYeop Kim
Diffusion은 신이고 GPT는 무적이다
You may also enjoy
[논문리뷰] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
REPA 논문 리뷰 (ICLR 2025 Oral)
Tags: Computer Vision, Diffusion, DiT, ICLR, Image Generation
[논문리뷰] Spherical Voronoi: Directional Appearance as a Differentiable Partition of the Sphere
Spherical Voronoi 논문 리뷰
Tags: 3D Reconstruction, 3D Vision, Gaussian Splatting, Novel View Synthesis
[논문리뷰] D²USt3R: Enhancing 3D Reconstruction for Dynamic Scenes
D²USt3R 논문 리뷰 (NeurIPS 2025)
Tags: 3D Reconstruction, 3D Vision, DUSt3R, NeurIPS, Pose Estimation
[논문리뷰] Light-A-Video: Training-free Video Relighting via Progressive Light Fusion
Light-A-Video 논문 리뷰 (ICCV 2025)
Tags: Computer Vision, Diffusion, ICCV