2 papers
cs.CV2026
RS-Prune: Read-Sparse, Store-Sparse Token Pruning for Video Object Segmentation
Avilasha Mandal, Sarvesh Shashikumar
We introduce RS-Prune, a training-free token-pruning recipe that instantiates as a small set of inference time hooks atop existing video object segmentation (VOS) networks. Mod…
cs.CV2026
Attend what matters: Leveraging vision foundational models for breast cancer classification using mammograms
Samyak Sanghvi, Piyush Miglani, Sarvesh Shashikumar +3
Vision Transformers have become the architecture of choice for many computer vision tasks, yet their performance in computer-aided diagnostics remains limited. Foc…