[논문리뷰] Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions
∆ConvFusion 논문 리뷰 (ICCV 2025)
Recent posts
[논문리뷰] Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think
REG 논문 리뷰 (NeurIPS 2025 Oral)
[PC] 리듬 닥터
Rhythm Doctor - 100% 클리어
[논문리뷰] Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models
Guidance Interval 논문 리뷰 (NeurIPS 2024)
[논문리뷰] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
REPA 논문 리뷰 (ICLR 2025 Oral)