Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
Chain-of-Image Generation: Toward Monitorable and Controllable Image Generation
Young Kyung Kim, Oded Schlesinger, Yuzhou Zhao +2
While state-of-the-art image generation models achieve remarkable visual quality, their internal generative processes remain a "black box." This opacity limits human observation an…
cs.CV2025
SPOT: Sparsification with Attention Dynamics via Token Relevance in Vision Transformers
Oded Schlesinger, Amirhossein Farzam, J. Matias Di Martino +1
While Vision Transformers (ViT) have demonstrated remarkable performance across diverse tasks, their computational demands are substantial, scaling quadratically with the number of…