[논문리뷰] DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
DeCo 논문 리뷰 (CVPR 2026 Highlight)
Recent posts
[논문리뷰] MakeAnything: Harnessing Diffusion Transformers for Multi-Domain Procedural Sequence Generation
MakeAnything 논문 리뷰 (CVPR 2026)
[논문리뷰] GeoSAM2: Unleashing the Power of SAM2 for 3D Part Segmentation
GeoSAM2 논문 리뷰 (CVPR 2026)
[논문리뷰] LATTICE: Democratize High-Fidelity 3D Generation at Scale
LATTICE 논문 리뷰 (CVPR 2026)
[논문리뷰] SRPO: Self-Referential Policy Optimization for Vision-Language-Action Models
SRPO 논문 리뷰 (CVPR 2026)