activity
20242026
collaborators

5 papers

cs.CV2026

Dynamic Mode Decomposition along Depth in Vision Transformers

Nishant Suresh Aswani, Saif Eddin Jabari

Recent work has shown that contiguous vision transformer (ViT) blocks (a) can be replaced by a linear map and (b) organize into recurrent phases of computation. We ask whether thes…

cs.LG2025

Koopman Autoencoders Learn Neural Representation Dynamics

Nishant Suresh Aswani, Saif Eddin Jabari

This paper explores a simple question: can we model the internal transformations of a neural network using dynamical systems theory? We introduce Koopman autoencoders to capture ho…

cs.LG2024

Representing Neural Network Layers as Linear Operations via Koopman Operator Theory

Nishant Suresh Aswani, Saif Eddin Jabari, Muhammad Shafique

The strong performance of simple neural networks is often attributed to their nonlinear activations. However, a linear view of neural networks makes understanding and controlling n…

cs.CV2024

Exploring the Interplay of Interpretability and Robustness in Deep Neural Networks: A Saliency-guided Approach

Amira Guesmi, Nishant Suresh Aswani, Muhammad Shafique

Adversarial attacks pose a significant challenge to deploying deep learning models in safety-critical applications. Maintaining model robustness while ensuring interpretability is…

cs.LG2024

Examining Changes in Internal Representations of Continual Learning Models Through Tensor Decomposition

Nishant Suresh Aswani, Amira Guesmi, Muhammad Abdullah Hanif +1

Continual learning (CL) has spurred the development of several methods aimed at consolidating previous knowledge across sequential learning. Yet, the evaluations of these methods h…