2 papers
cs.IT2026
Why Self-Supervised Encoders Want to Be Normal
Yuval Domb
Self-supervised learning has achieved remarkable empirical success in learning robust representations without explicit labels, most recently demonstrated within the framework of Jo…
cs.CV2025
LiteAttention: A Temporal Sparse Attention for Diffusion Transformers
Dor Shmilovich, Tony Wu, Aviad Dahan +1
Diffusion Transformers, particularly for video generation, achieve remarkable quality but suffer from quadratic attention complexity, leading to prohibitive latency. Existing accel…