99 citations · 702 across the 46 of their papers we have counts for
47 papers
ReferFlow: Beyond Final-Target Localization for Complex Referring Expressions
Tianyi Gao, Han Fang, Xin Wei +11
Multimodal Large Language Models have made significant progress in referring expression comprehension (REC), yet most REC benchmarks still focus on final-target localization. Compl…
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…
Efficient Dilated Squeeze and Excitation Neural Operator for Differential Equations
Prajwal Chauhan, Salah Eddine Choutri, Saif Eddin Jabari
Fast and accurate surrogates for physics-driven partial differential equations (PDEs) are essential in fields such as aerodynamics, porous media design, and flow control. However,…
Monte Carlo-Type Neural Operator for Differential Equations
Salah Eddine Choutri, Prajwal Chauhan, Othmane Mazhar +1
The Monte Carlo-type Neural Operator (MCNO) introduces a framework for learning solution operators of one-dimensional partial differential equations (PDEs) by directly learning the…
Learning Solution Operators for Partial Differential Equations via Monte Carlo-Type Approximation
Salah Eddine Choutri, Prajwal Chauhan, Othmane Mazhar +1
The Monte Carlo-type Neural Operator (MCNO) introduces a lightweight architecture for learning solution operators for parametric PDEs by directly approximating the kernel integral…
Backpressure-based Mean-field Type Game for Scheduling in Multi-Hop Wireless Sensor Networks
Salah Eddine Choutri, Boualem Djehiche, Prajwal Chauhan +1
We propose a Mean-Field Type Game (MFTG) framework for effective scheduling in multi-hop wireless sensor networks (WSNs) using backpressure as a performance criterion. Traditional…
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…
Neural operators struggle to learn complex PDEs in pedestrian mobility: Hughes model case study
Prajwal Chauhan, Salah Eddine Choutri, Mohamed Ghattassi +2
This paper investigates the limitations of neural operators in learning solutions for a Hughes model, a first-order hyperbolic conservation law system for crowd dynamics. The model…
FlowMixer: A Depth-Agnostic Neural Architecture for Interpretable Spatiotemporal Forecasting
Fares B. Mehouachi, Saif Eddin Jabari
We introduce FlowMixer, a single-layer neural architecture that leverages constrained matrix operations to model structured spatiotemporal patterns with enhanced interpretability.…
Catastrophic Overfitting, Entropy Gap and Participation Ratio: A Noiseless Norm Solution for Fast Adversarial Training
Fares B. Mehouachi, Saif Eddin Jabari
Adversarial training is a cornerstone of robust deep learning, but fast methods like the Fast Gradient Sign Method (FGSM) often suffer from Catastrophic Overfitting (CO), where mod…
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…
Urban traffic analysis and forecasting through shared Koopman eigenmodes
Chuhan Yang, Fares B. Mehouachi, Monica Menendez +1
Predicting traffic flow in data-scarce cities is challenging due to limited historical data. To address this, we leverage transfer learning by identifying periodic patterns common…
Countering adversarial perturbations in graphs using error correcting codes
Saif Eddin Jabari
We consider the problem of a graph subjected to adversarial perturbations, such as those arising from cyber-attacks, where edges are covertly added or removed. The adversarial pert…
On the Role of Non-Localities in Fundamental Diagram Estimation
Jing Liu, Fangfang Zheng, Boxi Yu +1
We consider the role of non-localities in speed-density data used to fit fundamental diagrams from vehicle trajectories. We demonstrate that the use of anticipated densities result…
Fourier neural operator for learning solutions to macroscopic traffic flow models: Application to the forward and inverse problems
Bilal Thonnam Thodi, Sai Venkata Ramana Ambadipudi, Saif Eddin Jabari
Deep learning methods are emerging as popular computational tools for solving forward and inverse problems in traffic flow. In this paper, we study a neural operator framework for…
Physical Backdoor Trigger Activation of Autonomous Vehicle using Reachability Analysis
Wenqing Li, Yue Wang, Muhammad Shafique +1
Recent studies reveal that Autonomous Vehicles (AVs) can be manipulated by hidden backdoors, causing them to perform harmful actions when activated by physical triggers. However, i…
Optimal Smoothing Distribution Exploration for Backdoor Neutralization in Deep Learning-based Traffic Systems
Yue Wang, Wending Li, Michail Maniatakos +1
Deep Reinforcement Learning (DRL) enhances the efficiency of Autonomous Vehicles (AV), but also makes them susceptible to backdoor attacks that can result in traffic congestion or…
Learning-based solutions to nonlinear hyperbolic PDEs: Empirical insights on generalization errors
Bilal Thonnam Thodi, Sai Venkata Ramana Ambadipudi, Saif Eddin Jabari
We study learning weak solutions to nonlinear hyperbolic partial differential equations (H-PDE), which have been difficult to learn due to discontinuities in their solutions. We us…
Generalized adaptive smoothing based neural network architecture for traffic state estimation
Chuhan Yang, Sai Venkata Ramana Ambadipudi, Saif Eddin Jabari
The adaptive smoothing method (ASM) is a standard data-driven technique used in traffic state estimation. The ASM has free parameters which, in practice, are chosen to be some gene…
Stationary states in two lane traffic: insights from kinetic theory
A. Sai Venkata Ramana, Saif Eddin Jabari
Kinetics of dilute heterogeneous traffic on a two lane road is formulated in the framework of the Ben-Naim Krapivsky model and stationary state properties are analytically derived…
Generalized Adaptive Smoothing Using Matrix Completion for Traffic State Estimation
Chuhan Yang, Bilal Thonnam Thodi, Saif Eddin Jabari
The Adaptive Smoothing Method (ASM) is a data-driven approach for traffic state estimation. It interpolates unobserved traffic quantities by smoothing measurements along spatio-tem…
PiDAn: A Coherence Optimization Approach for Backdoor Attack Detection and Mitigation in Deep Neural Networks
Yue Wang, Wenqing Li, Esha Sarkar +3
Backdoor attacks impose a new threat in Deep Neural Networks (DNNs), where a backdoor is inserted into the neural network by poisoning the training dataset, misclassifying inputs t…
Learning Traffic Speed Dynamics from Visualizations
Bilal Thonnam Thodi, Zaid Saeed Khan, Saif Eddin Jabari +1
Space-time visualizations of macroscopic or microscopic traffic variables is a qualitative tool used by traffic engineers to understand and analyze different aspects of road traffi…
Power laws and phase transitions in heterogenous car following with reaction times
A. Sai Venkata Ramana, Saif Eddin Jabari
We study the effect of reaction times on the kinetics of relaxation to stationary states and on congestion transitions in heterogeneous traffic. Heterogeneity is modeled as quenche…