JiYeop Kim
Diffusion은 신이고 GPT는 무적이다
You may also enjoy
[논문리뷰] D-Attn: Decomposed Attention for Large Vision-and-Language Models
Decomposed Attention (D-Attn) 논문 리뷰 (ICCV 2025)
[논문리뷰] Efficient Track Anything
EfficientTAM 논문 리뷰 (ICCV 2025)
Tags: Computer Vision, ICCV, Meta, Video Object Segmentation
[논문리뷰] Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think
Diffusion end-to-end fine-tuning (E2E FT) 논문 리뷰 (WACV 2025 Oral)
Tags: Computer Vision, Diffusion, Monocular Depth Estimation
[논문리뷰] SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling
SparseFlex (TripoSF) 논문 리뷰 (ICCV 2025 Oral)
Tags: 3D Vision, ICCV, Mesh Generation