17 citations · 21 across the 14 of their papers we have counts for
16 papers
Graph-Spectral Flow Matching for Multivariate Time Series Anomaly Detection
Zepeng Zhang, Jhony H. Giraldo, Wenbin Wang +1
Multivariate time series anomaly detection typically relies on evaluating discrepancies between observations and outputs produced by models trained on normal data. An alternative p…
GSLAD: Prototype-Regularized Graph Structure Learning for Multivariate Time Series Anomaly Detection
Zepeng Zhang, Fuad Khuri, Keivan Faghih Niresi +1
Unsupervised multivariate time series anomaly detection methods typically identify anomalies through forecasting, reconstruction, or representation discrepancies. However, industri…
Agentic Root Cause Analysis through Evidence-Grounded Reasoning
Amaury Wei, Olga Fink
Diagnosing the root cause of anomalies is essential for safe industrial operation. Despite extensive sensor instrumentation, formulating hypotheses and gathering evidence remains a…
Neural Kolmogorov Equations: Parallelizable Learning of Stochastic Dynamics under General Noise
Arthur Bizzi, Olga Fink
Neural stochastic differential equations (SDEs) have emerged as powerful tools for learning noisy or stochastic dynamics directly from data; however, existing approaches largely as…
Beyond Thermal Imaging: Inferring Thermophysical Properties from Time-Resolved Thermal Observations
Chenghao Xu, Malcolm Mielle, Olga Fink
Inferring latent physical properties from sensory observations is a fundamental challenge in machine perception. Among available sensing modalities, thermal imaging is particularly…
In-Context Residual Calibration for Uncertainty Quantification of Energy Time Series over Graphs
Keivan Faghih Niresi, Alice Cicirello, Olga Fink
Accurate energy demand forecasting is essential for the reliable operation and planning of modern sustainable energy systems. Spatial-temporal graph neural networks (STGNNs) have r…
Rethinking Object-Centric Representations for Video Dynamics Modeling
Amaury Wei, Ismail Nejjar, Olga Fink
Learning to decompose videos into persistent objects is a fundamental challenge in unsupervised object-centric representation learning. Despite recent progress, existing methods st…
Unpaired RGB-Thermal Gaussian-Splatting Using Visual Geometric Transformers
Jean Cordonnier, Chenghao Xu, Olga Fink +1
Multi-modal novel view synthesis (NVS) combining RGB and thermal imagery enables precise 3D scene reconstruction with visual and thermal information. However, existing methods typi…
Graph Signal Separation with Learnable Spectral Filters
Keivan Faghih Niresi, Dorina Thanou, Olga Fink
Separating multiple graph signals from a single observed mixture is an inherently ill-posed problem that traditionally relies on restrictive and handcrafted priors. This letter add…
SEAR: Simple and Efficient Adaptation of Visual Geometric Transformers for Unpaired RGB+Thermal 3D Reconstruction
Vsevolod Skorokhodov, Chenghao Xu, Shuo Sun +2
Foundational feed-forward visual geometry models enable accurate and efficient camera pose estimation and scene reconstruction by learning strong scene priors from massive RGB data…
Time-Vertex Machine Learning for Optimal Sensor Placement in Temporal Graph Signals: Applications in Structural Health Monitoring
Keivan Faghih Niresi, Jun Qing, Mengjie Zhao +1
Structural Health Monitoring (SHM) plays a crucial role in maintaining the safety and resilience of infrastructure. As sensor networks grow in scale and complexity, identifying the…
RINS-T: Robust Implicit Neural Solvers for Time Series Linear Inverse Problems
Keivan Faghih Niresi, Zepeng Zhang, Olga Fink
Time series data are often affected by various forms of corruption, such as missing values, noise, and outliers, which pose significant challenges for tasks such as forecasting and…
From Physics to Machine Learning and Back: Part II - Learning and Observational Bias in PHM
Olga Fink, Ismail Nejjar, Vinay Sharma +13
Prognostics and Health Management ensures the reliability, safety, and efficiency of complex engineered systems by enabling fault detection, anticipating equipment failures, and op…
Efficient Unsupervised Domain Adaptation Regression for Spatial-Temporal Sensor Fusion
Keivan Faghih Niresi, Ismail Nejjar, Olga Fink
The growing deployment of low-cost, distributed sensor networks in environmental and biomedical domains has enabled continuous, large-scale health monitoring. However, these system…
Physics-Enhanced Graph Neural Networks For Soft Sensing in Industrial Internet of Things
Keivan Faghih Niresi, Hugo Bissig, Henri Baumann +1
The Industrial Internet of Things (IIoT) is reshaping manufacturing, industrial processes, and infrastructure management. By fostering new levels of automation, efficiency, and pre…
Spatial-Temporal Graph Attention Fuser for Calibration in IoT Air Pollution Monitoring Systems
Keivan Faghih Niresi, Mengjie Zhao, Hugo Bissig +2
The use of Internet of Things (IoT) sensors for air pollution monitoring has significantly increased, resulting in the deployment of low-cost sensors. Despite this advancement, acc…