2 papers
cs.CV2026
Explainability-Inspired Layer-Wise Pruning of Deep Neural Networks for Efficient Object Detection
Abhinav Shukla, Nachiket Tapas
Deep neural networks (DNNs) have achieved remarkable success in object detection tasks, but their increasing complexity poses significant challenges for deployment on resource-cons…
cs.LG2024
MatMamba: A Matryoshka State Space Model
Abhinav Shukla, Sai Vemprala, Aditya Kusupati +1
State Space Models (SSMs) like Mamba2 are a promising alternative to Transformers, with faster theoretical training and inference times -- especially for long context lengths. Rece…