arXiv subjects

Eleni Chatzi

Publications and source records attributed to Eleni Chatzi.

At least 37 records · Page 2Linked to original sources

arXiv2025

Causal Convolutional Neural Networks as Finite Impulse Response Filters

This study investigates the behavior of Causal Convolutional Neural Networks (CNNs) with quasi-linear activation functions when applied to time-series data characterized by multimodal frequency content. We demonstrate that, once trained, such networks exhibit properties analogous to Finite Impulse Response (FIR) filters, particularly when the convolutional kernels are of extended length exceeding those typically employed in standard CNN architectures. Causal CNNs are shown to capture spectral features both implicitly and explicitly, offering enhanced interpretability for tasks involving dynamic systems. Leveraging the associative property of convolution, we further show that the entire network can be reduced to an equivalent single-layer filter resembling an FIR filter optimized via least-squares criteria. This equivalence yields new insights into the spectral learning behavior of CNNs trained on signals with sparse frequency content. The approach is validated on both simulated beam dynamics and real-world bridge vibration datasets, underlining its relevance for modeling and identifying physical systems governed by dynamic responses.

cs.LG↗

arXiv2025

To Trust Or Not To Trust Your Vision-Language Model's Prediction

Vision-Language Models (VLMs) have demonstrated strong capabilities in aligning visual and textual modalities, enabling a wide range of applications in multimodal understanding and generation. While they excel in zero-shot and transfer learning scenarios, VLMs remain susceptible to misclassification, often yielding confident yet incorrect predictions. This limitation poses a significant risk in safety-critical domains, where erroneous predictions can lead to severe consequences. In this work, we introduce TrustVLM, a training-free framework designed to address the critical challenge of estimating when VLM's predictions can be trusted. Motivated by the observed modality gap in VLMs and the insight that certain concepts are more distinctly represented in the image embedding space, we propose a novel confidence-scoring function that leverages this space to improve misclassification detection. We rigorously evaluate our approach across 17 diverse datasets, employing 4 architectures and 2 VLMs, and demonstrate state-of-the-art performance, with improvements of up to 51.87% in AURC, 9.14% in AUROC, and 32.42% in FPR95 compared to existing baselines. By improving the reliability of the model without requiring retraining, TrustVLM paves the way for safer deployment of VLMs in real-world applications. The code is available at https://github.com/EPFL-IMOS/TrustVLM.

cs.CV↗

arXiv2025

Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models

In real-world scenarios, achieving domain adaptation and generalization poses significant challenges, as models must adapt to or generalize across unknown target distributions. Extending these capabilities to unseen multimodal distributions, i.e., multimodal domain adaptation and generalization, is even more challenging due to the distinct characteristics of different modalities. Significant progress has been made over the years, with applications ranging from action recognition to semantic segmentation. Besides, the recent advent of large-scale pre-trained multimodal foundation models, such as CLIP, has inspired works leveraging these models to enhance adaptation and generalization performances or adapting them to downstream tasks. This survey provides the first comprehensive review of recent advances from traditional approaches to foundation models, covering: (1) Multimodal domain adaptation; (2) Multimodal test-time adaptation; (3) Multimodal domain generalization; (4) Domain adaptation and generalization with the help of multimodal foundation models; and (5) Adaptation of multimodal foundation models. For each topic, we formally define the problem and thoroughly review existing methods. Additionally, we analyze relevant datasets and applications, highlighting open challenges and potential future research directions. We maintain an active repository that contains up-to-date literature at https://github.com/donghao51/Awesome-Multimodal-Adaptation.

cs.CV↗

arXiv2025

Quantifying the Value of Seismic Structural Health Monitoring for post-earthquake recovery of electric power system in terms of resilience enhancement

Post-earthquake recovery of electric power networks (EPNs) is critical to community resilience. Traditional recovery processes often rely on prolonged and imprecise manual inspections for damage diagnosis, leading to suboptimal repair prioritization and extended service disruptions. Seismic Structural Health Monitoring (SSHM) offers the potential to expedite recovery by enabling more accurate and timely damage assessment. However, SSHM deployment incurs costs, and its system-level resilience benefit remains underexplored. This study proposes a probabilistic simulation framework to quantify the value of SSHM for enhancing EPN resilience. The framework includes seismic damage modeling based on network configuration, hazard intensity, fragility functions, and damage-functionality mappings, combined with recovery simulations incorporating resource constraints, repair and transfer durations. System functionality is evaluated using graph-based island detection and optimal power flow analysis. Resilience is quantified via the Lack of Resilience (LoR) metric derived from the functionality restoration curve. SSHM is incorporated by altering the quality of damage information used in repair scheduling. Different monitoring scenarios (e.g., no-SSHM baseline, partial SSHM, full SSHM with various accuracies) are modeled using confusion matrices to simulate damage misclassification. Results show that improved damage awareness via SSHM significantly accelerates recovery and reduces LoR by up to 21%. This work supports evidence-based decisions for SSHM deployment in critical infrastructure.

eess.SY↗

arXiv2025

A Multi-Model Probabilistic Framework for Seismic Risk Assessment and Retrofit Planning of Electric Power Networks

Electric power networks are critical lifelines, and their disruption during earthquakes can lead to severe cascading failures and significantly hinder post-disaster recovery. Enhancing their seismic resilience requires identifying and strengthening vulnerable components in a cost-effective and system-aware manner. However, existing studies often overlook the systemic behavior of power networks under seismic loading. Common limitations include isolated component analyses that neglect network-wide interdependencies, oversimplified damage models assuming binary states or damage independence, and the exclusion of electrical operational constraints. These simplifications can result in inaccurate risk estimates and inefficient retrofit decisions. This study proposes a multi-model probabilistic framework for seismic risk assessment and retrofit planning of electric power systems. The approach integrates: (1) regional seismic hazard characterization with ground motion prediction and spatial correlation models; (2) component-level damage analysis using fragility functions and multi-state damage-functionality mappings; (3) system-level cascading impact evaluation through graph-based island detection and constrained optimal power flow analysis; and (4) retrofit planning via heuristic optimization to minimize expected annual functionality loss (EAFL) under budget constraints. Uncertainty is propagated throughout the framework using Monte Carlo simulation. The methodology is demonstrated on the IEEE 24-bus Reliability Test System, showcasing its ability to capture cascading failures, identify critical components, and generate effective retrofit strategies. Results underscore the potential of the framework as a scalable, data-informed decision-support tool for enhancing the seismic resilience of power infrastructure.

eess.SY↗

arXiv2025

Adapting Vision-Language Models Without Labels: A Comprehensive Survey

Vision-Language Models (VLMs) have demonstrated remarkable generalization capabilities across a wide range of tasks. However, their performance often remains suboptimal when directly applied to specific downstream scenarios without task-specific adaptation. To enhance their utility while preserving data efficiency, recent research has increasingly focused on unsupervised adaptation methods that do not rely on labeled data. Despite the growing interest in this area, there remains a lack of a unified, task-oriented survey dedicated to unsupervised VLM adaptation. To bridge this gap, we present a comprehensive and structured overview of the field. We propose a taxonomy based on the availability and nature of unlabeled visual data, categorizing existing approaches into four key paradigms: Data-Free Transfer (no data), Unsupervised Domain Transfer (abundant data), Episodic Test-Time Adaptation (batch data), and Online Test-Time Adaptation (streaming data). Within this framework, we analyze core methodologies and adaptation strategies associated with each paradigm, aiming to establish a systematic understanding of the field. Additionally, we review representative benchmarks across diverse applications and highlight open challenges and promising directions for future research. An actively maintained repository of relevant literature is available at https://github.com/tim-learn/Awesome-LabelFree-VLMs.

cs.LG↗

arXiv2025

Resilience-based post disaster recovery optimization for infrastructure system via Deep Reinforcement Learning

Infrastructure systems are critical in modern communities but are highly susceptible to various natural and man-made disasters. Efficient post-disaster recovery requires repair-scheduling approaches under the limitation of capped resources that need to be shared across the system. Existing approaches, including component ranking methods, greedy evolutionary algorithms, and data-driven machine learning models, face various limitations when tested within such a context. To tackle these issues, we propose a novel approach to optimize post-disaster recovery of infrastructure systems by leveraging Deep Reinforcement Learning (DRL) methods and incorporating a specialized resilience metric to lead the optimization. The system topology is represented adopting a graph-based structure, where the system's recovery process is formulated as a sequential decision-making problem. Deep Q-learning algorithms are employed to learn optimal recovery strategies by mapping system states to specific actions, as for instance which component ought to be repaired next, with the goal of maximizing long-term recovery from a resilience-oriented perspective. To demonstrate the efficacy of our proposed approach, we implement this scheme on the example of post-earthquake recovery optimization for an electrical substation system. We assess different deep Q-learning algorithms to this end, namely vanilla Deep Q-Networks (DQN), Double DQN(DDQN), Duel DQN, and duel DDQN, demonstrating superiority of the DDQN for the considered problem. A further comparative analysis against baseline methods during testing reveals the superior performance of the proposed method in terms of both optimization effect and computational cost, rendering this an attractive approach in the context of resilience enhancement and rapid response and recovery.

cs.CE↗

arXiv2025

Spatial and Temporal Characterization of Living Mycelium through Dispersion Analysis

Mycelium, a natural and sustainable material, possesses unique electrical, mechanical, and biological properties that make it a promising candidate for biosensor applications. These properties include its ability to conduct electrical signals, respond to external stimuli such as humidity and mechanical stress, and grow integrally within structures to form a natural network. Such characteristics suggest its potential for integration into self-sensing systems to monitor vibrations, deformations, and environmental conditions in buildings and infrastructure. To understand the output voltage generated by these biomaterials in response to an applied electrical input, it is essential to characterize their spatial and temporal properties. This study introduces an electrical impedance network model to describe signal transmission through mycelium. In combination with the inhomogeneous wave correlation (IWC) method, commonly used in elastic wave propagation, we demonstrate the dispersion behavior of living mycelium both theoretically and experimentally. We reveal the frequency-dependent and spatial attenuation of electrical signals in living, dehydrated, and rehydrated mycelium, emphasizing the critical role of humidity in enabling effective signal sensing. Furthermore, dispersion analysis is used to assess the homogeneity of mycelium, underscoring its feasibility as a living, green sensing material. This research lays the groundwork for innovative applications of mycelium in sustainable structural health monitoring.

physics.app-ph↗

arXiv2025

Modal Decomposition and Identification for a Population of Structures Using Physics-Informed Graph Neural Networks and Transformers

Modal identification is crucial for structural health monitoring and structural control, providing critical insights into structural dynamics and performance. This study presents a novel deep learning framework that integrates graph neural networks (GNNs), transformers, and a physics-informed loss function to achieve modal decomposition and identification across a population of structures. The transformer module decomposes multi-degrees-of-freedom (MDOF) structural dynamic measurements into single-degree-of-freedom (SDOF) modal responses, facilitating the identification of natural frequencies and damping ratios. Concurrently, the GNN captures the structural configurations and identifies mode shapes corresponding to the decomposed SDOF modal responses. The proposed model is trained in a purely physics-informed and unsupervised manner, leveraging modal decomposition theory and the independence of structural modes to guide learning without the need for labeled data. Validation through numerical simulations and laboratory experiments demonstrates its effectiveness in accurately decomposing dynamic responses and identifying modal properties from sparse structural dynamic measurements, regardless of variations in external loads or structural configurations. Comparative analyses against established modal identification techniques and model variations further underscore its superior performance, positioning it as a favorable approach for population-based structural health monitoring.

cs.CE↗

arXiv2025

A Reduced Order Model conditioned on monitoring features for estimation and uncertainty quantification in engineered systems

Reduced Order Models (ROMs) form essential tools across engineering domains by virtue of their function as surrogates for computationally intensive digital twinning simulators. Although purely data-driven methods are available for ROM construction, schemes that allow to retain a portion of the physics tend to enhance the interpretability and generalization of ROMs. However, physics-based techniques can adversely scale when dealing with nonlinear systems that feature parametric dependencies. This study introduces a generative physics-based ROM that is suited for nonlinear systems with parametric dependencies and is additionally able to quantify the confidence associated with the respective estimates. A main contribution of this work is the conditioning of these parametric ROMs to features that can be derived from monitoring measurements, feasibly in an online fashion. This is contrary to most existing ROM schemes, which remain restricted to the prescription of the physics-based, and usually a priori unknown, system parameters. Our work utilizes conditional Variational Autoencoders to continuously map the required reduction bases to a feature vector extracted from limited output measurements, while additionally allowing for a probabilistic assessment of the ROM-estimated Quantities of Interest. An auxiliary task using a neural network-based parametrization of suitable probability distributions is introduced to re-establish the link with physical model parameters. We verify the proposed scheme on a series of simulated case studies incorporating effects of geometric and material nonlinearity under parametric dependencies related to system properties and input load characteristics.

cs.CE↗

arXiv2025

Grammar-based Ordinary Differential Equation Discovery

The understanding and modeling of complex physical phenomena through dynamical systems has historically driven scientific progress, as it provides the tools for predicting the behavior of different systems under diverse conditions through time. The discovery of dynamical systems has been indispensable in engineering, as it allows for the analysis and prediction of complex behaviors for computational modeling, diagnostics, prognostics, and control of engineered systems. Joining recent efforts that harness the power of symbolic regression in this domain, we propose a novel framework for the end-to-end discovery of ordinary differential equations (ODEs), termed Grammar-based ODE Discovery Engine (GODE). The proposed methodology combines formal grammars with dimensionality reduction and stochastic search for efficiently navigating high-dimensional combinatorial spaces. Grammars allow us to seed domain knowledge and structure for both constraining, as well as, exploring the space of candidate expressions. GODE proves to be more sample- and parameter-efficient than state-of-the-art transformer-based models and to discover more accurate and parsimonious ODE expressions than both genetic programming- and other grammar-based methods for more complex inference tasks, such as the discovery of structural dynamics. Thus, we introduce a tool that could play a catalytic role in dynamics discovery tasks, including modeling, system identification, and monitoring tasks.

cs.LG↗

arXiv2025

Deep Belief Markov Models for POMDP Inference

This work introduces a novel deep learning-based architecture, termed the Deep Belief Markov Model (DBMM), which provides efficient, model-formulation agnostic inference in Partially Observable Markov Decision Process (POMDP) problems. The POMDP framework allows for modeling and solving sequential decision-making problems under observation uncertainty. In complex, high-dimensional, partially observable environments, existing methods for inference based on exact computations (e.g., via Bayes' theorem) or sampling algorithms do not scale well. Furthermore, ground truth states may not be available for learning the exact transition dynamics. DBMMs extend deep Markov models into the partially observable decision-making framework and allow efficient belief inference entirely based on available observation data via variational inference methods. By leveraging the potency of neural networks, DBMMs can infer and simulate non-linear relationships in the system dynamics and naturally scale to problems with high dimensionality and discrete or continuous variables. In addition, neural network parameters can be dynamically updated efficiently based on data availability. DBMMs can thus be used to infer a belief variable, thus enabling the derivation of POMDP solutions over the belief space. We evaluate the efficacy of the proposed methodology by evaluating the capability of model-formulation agnostic inference of DBMMs in benchmark problems that include discrete and continuous variables.

cs.LG↗

arXiv2025

Graph Transformers for inverse physics: reconstructing flows around arbitrary 2D airfoils

We introduce a Graph Transformer framework that serves as a general inverse physics engine on meshes, demonstrated through the challenging task of reconstructing aerodynamic flow fields from sparse surface measurements. While deep learning has shown promising results in forward physics simulation, inverse problems remain particularly challenging due to their ill-posed nature and the difficulty of propagating information from limited boundary observations. Our approach addresses these challenges by combining the geometric expressiveness of message-passing neural networks with the global reasoning of Transformers, enabling efficient learning of inverse mappings from boundary conditions to complete states. We evaluate this framework on a comprehensive dataset of steady-state RANS simulations around diverse airfoil geometries, where the task is to reconstruct full pressure and velocity fields from surface pressure measurements alone. The architecture achieves high reconstruction accuracy while maintaining fast inference times. We conduct experiments and provide insights into the relative importance of local geometric processing and global attention mechanisms in mesh-based inverse problems. We also find that the framework is robust to reduced sensor coverage. These results suggest that Graph Transformers can serve as effective inverse physics engines across a broader range of applications where complete system states must be reconstructed from limited boundary observations.

cs.LG↗

arXiv2025

Towards Robust Multimodal Open-set Test-time Adaptation via Adaptive Entropy-aware Optimization

Test-time adaptation (TTA) has demonstrated significant potential in addressing distribution shifts between training and testing data. Open-set test-time adaptation (OSTTA) aims to adapt a source pre-trained model online to an unlabeled target domain that contains unknown classes. This task becomes more challenging when multiple modalities are involved. Existing methods have primarily focused on unimodal OSTTA, often filtering out low-confidence samples without addressing the complexities of multimodal data. In this work, we present Adaptive Entropy-aware Optimization (AEO), a novel framework specifically designed to tackle Multimodal Open-set Test-time Adaptation (MM-OSTTA) for the first time. Our analysis shows that the entropy difference between known and unknown samples in the target domain strongly correlates with MM-OSTTA performance. To leverage this, we propose two key components: Unknown-aware Adaptive Entropy Optimization (UAE) and Adaptive Modality Prediction Discrepancy Optimization (AMP). These components enhance the ability of model to distinguish unknown class samples during online adaptation by amplifying the entropy difference between known and unknown samples. To thoroughly evaluate our proposed methods in the MM-OSTTA setting, we establish a new benchmark derived from existing datasets. This benchmark includes two downstream tasks and incorporates five modalities. Extensive experiments across various domain shift situations demonstrate the efficacy and versatility of the AEO framework. Additionally, we highlight the strong performance of AEO in long-term and continual MM-OSTTA settings, both of which are challenging and highly relevant to real-world applications. Our source code is available at https://github.com/donghao51/AEO.

cs.CV↗

arXiv2024

Response Estimation and System Identification of Dynamical Systems via Physics-Informed Neural Networks

The accurate modelling of structural dynamics is crucial across numerous engineering applications, such as Structural Health Monitoring (SHM), seismic analysis, and vibration control. Often, these models originate from physics-based principles and can be derived from corresponding governing equations, often of differential equation form. However, complex system characteristics, such as nonlinearities and energy dissipation mechanisms, often imply that such models are approximative and often imprecise. This challenge is further compounded in SHM, where sensor data is often sparse, making it difficult to fully observe the system's states. To address these issues, this paper explores the use of Physics-Informed Neural Networks (PINNs), a class of physics-enhanced machine learning (PEML) techniques, for the identification and estimation of dynamical systems. PINNs offer a unique advantage by embedding known physical laws directly into the neural network's loss function, allowing for simple embedding of complex phenomena, even in the presence of uncertainties. This study specifically investigates three key applications of PINNs: state estimation in systems with sparse sensing, joint state-parameter estimation, when both system response and parameters are unknown, and parameter estimation within a Bayesian framework to quantify uncertainties. The results demonstrate that PINNs deliver an efficient tool across all aforementioned tasks, even in presence of modelling errors. However, these errors tend to have a more significant impact on parameter estimation, as the optimization process must reconcile discrepancies between the prescribed model and the true system behavior. Despite these challenges, PINNs show promise in dynamical system modeling, offering a robust approach to handling uncertainties.

physics.comp-ph↗

arXiv2024

MultiOOD: Scaling Out-of-Distribution Detection for Multiple Modalities

Detecting out-of-distribution (OOD) samples is important for deploying machine learning models in safety-critical applications such as autonomous driving and robot-assisted surgery. Existing research has mainly focused on unimodal scenarios on image data. However, real-world applications are inherently multimodal, which makes it essential to leverage information from multiple modalities to enhance the efficacy of OOD detection. To establish a foundation for more realistic Multimodal OOD Detection, we introduce the first-of-its-kind benchmark, MultiOOD, characterized by diverse dataset sizes and varying modality combinations. We first evaluate existing unimodal OOD detection algorithms on MultiOOD, observing that the mere inclusion of additional modalities yields substantial improvements. This underscores the importance of utilizing multiple modalities for OOD detection. Based on the observation of Modality Prediction Discrepancy between in-distribution (ID) and OOD data, and its strong correlation with OOD performance, we propose the Agree-to-Disagree (A2D) algorithm to encourage such discrepancy during training. Moreover, we introduce a novel outlier synthesis method, NP-Mix, which explores broader feature spaces by leveraging the information from nearest neighbor classes and complements A2D to strengthen OOD detection performance. Extensive experiments on MultiOOD demonstrate that training with A2D and NP-Mix improves existing OOD detection algorithms by a large margin. Our source code and MultiOOD benchmark are available at https://github.com/donghao51/MultiOOD.

cs.CV↗

arXiv2024

Using Graph Neural Networks and Frequency Domain Data for Automated Operational Modal Analysis of Populations of Structures

The Population-Based Structural Health Monitoring (PBSHM) paradigm has recently emerged as a promising approach to enhance data-driven assessment of engineering structures by facilitating transfer learning between structures with some degree of similarity. In this work, we apply this concept to the automated modal identification of structural systems. We introduce a Graph Neural Network (GNN)-based deep learning scheme to identify modal properties, including natural frequencies, damping ratios, and mode shapes of engineering structures based on the Power Spectral Density (PSD) of spatially-sparse vibration measurements. Systematic numerical experiments are conducted to evaluate the proposed model, employing two distinct truss populations that possess similar topological characteristics but varying geometric (size, shape) and material (stiffness) properties. The results demonstrate that, once trained, the proposed GNN-based model can identify modal properties of unseen structures within the same structural population with good efficiency and acceptable accuracy, even in the presence of measurement noise and sparse measurement locations. The GNN-based model exhibits advantages over the classic Frequency Domain Decomposition (FDD) method in terms of identification speed, as well as against an alternate Multi-Layer Perceptron (MLP) architecture in terms of identification accuracy, rendering this a promising tool for PBSHM purposes.

cs.CE↗

arXiv2024

Towards Multimodal Open-Set Domain Generalization and Adaptation through Self-supervision

The task of open-set domain generalization (OSDG) involves recognizing novel classes within unseen domains, which becomes more challenging with multiple modalities as input. Existing works have only addressed unimodal OSDG within the meta-learning framework, without considering multimodal scenarios. In this work, we introduce a novel approach to address Multimodal Open-Set Domain Generalization (MM-OSDG) for the first time, utilizing self-supervision. To this end, we introduce two innovative multimodal self-supervised pretext tasks: Masked Cross-modal Translation and Multimodal Jigsaw Puzzles. These tasks facilitate the learning of multimodal representative features, thereby enhancing generalization and open-class detection capabilities. Additionally, we propose a novel entropy weighting mechanism to balance the loss across different modalities. Furthermore, we extend our approach to tackle also the Multimodal Open-Set Domain Adaptation (MM-OSDA) problem, especially in scenarios where unlabeled data from the target domain is available. Extensive experiments conducted under MM-OSDG, MM-OSDA, and Multimodal Closed-Set DG settings on the EPIC-Kitchens and HAC datasets demonstrate the efficacy and versatility of the proposed approach. Our source code is available at https://github.com/donghao51/MOOSA.

cs.CV↗