collaborators

55 papers

cs.LG2026

Represent, Then Generate: Multimodal-Conditioned Time-Series Generation under Irregular Missingness

Haochen Zhang, Jiaheng Guo, Yu-Chao Huang +3

Continuous physiological time series underpin modern clinical monitoring, yet many of the most informative signals are invasive, expensive, or simply unavailable for a given patien…

cs.LG2026

Language Generation with Replay: A Learning-Theoretic View of Model Collapse

Giorgio Racca, Michal Valko, Amartya Sanyal

As scaling laws push the training of frontier large language models (LLMs) toward ever-growing data requirements, training pipelines are approaching a regime where much of the publ…

stat.ML2026

Spectral bandits for smooth graph functions with applications in recommender systems

Tomáš Kocák, Michal Valko, Rémi Munos +2

Smooth functions on graphs have wide applications in manifold and semi-supervised learning. In this paper, we study a bandit problem where the payoffs of arms are smooth on a graph…

cs.LG2026

Conditional anomaly detection methods for patient-management alert systems

Michal Valko, Gregory Cooper, Amy Seybert +3

Anomaly detection methods can be very useful in identifying unusual or interesting patterns in data. A recently proposed conditional anomaly detection framework extends anomaly det…

cs.LG2026

Learning predictive models for combinations of heterogeneous proteomic data sources

Michal Valko, Richard Pelikan, Miloš Hauskrecht

Multiple technologies that measure expression levels of protein mixtures in the human body offer a potential for detection and understanding the disease. The recent increase of the…

cs.LG2026

Outlier detection for patient monitoring and alerting

Miloš Hauskrecht, Iyad Batal, Michal Valko +3

We develop and evaluate a data-driven approach for detecting unusual (anomalous) patient-management decisions using past patient cases stored in electronic health records (EHRs). O…