3 papers
cs.CV2026
Provably Contractive and High-Quality Denoisers for Convergent Restoration
Shubhi Shukla, Pravin Nair
Image restoration, the recovery of clean images from degraded measurements, has applications in various domains like surveillance, defense, and medical imaging. Despite achieving s…
eess.IV2026
Plug-and-play linear attention with provable guarantees for training-free image restoration
Srinivasan Kidambi, Karthik Palaniappan, Pravin Nair
Multi-head self-attention (MHSA) is a key building block in modern vision Transformers, yet its quadratic complexity in the number of tokens remains a major bottleneck for real-tim…
cs.LG2025
Softmax is -Lipschitz: A tight bound across all norms
Pravin Nair
The softmax function is a basic operator in machine learning and optimization, used in classification, attention mechanisms, reinforcement learning, game theory, and problems invol…