6 papers
Discrete Wasserstein Flows for One-Step Generative Modeling
Alessandro Micheli, Andrea Zerio, Samir Bhatt
We introduce a new framework for one-step generative modelling on finite state spaces. To extend drifting beyond continuous domains, we use discrete Wasserstein geometry to define…
Sequence-Informed Geometric Evaluation of RNA 3D Structures
Andrea Zerio, Yighua Yao, Alessandro Micheli +5
Computational RNA structure pipelines generate many candidate conformations for the same sequence. Reliable evaluation therefore requires more than recognising plausible geometry,…
Graph Mixing Additive Networks
Maya Bechler-Speicher, Andrea Zerio, Maor Huri +5
We introduce GMAN, a flexible, interpretable, and expressive framework that extends Graph Neural Additive Networks (GNANs) to learn from sets of sparse time-series data. GMAN repre…
SuperMAN: Interpretable and Expressive Networks over Temporally Sparse Heterogeneous Data
Maya Bechler-Speicher, Andrea Zerio, Maor Huri +5
Real-world temporal data often consists of multiple signal types recorded at irregular, asynchronous intervals. For instance, in the medical domain, different types of blood tests…
Identifying Critical Phases for Disease Onset with Sparse Haematological Biomarkers
Andrea Zerio, Maya Bechler-Speicher, Tine Jess +1
Routinely collected clinical blood tests are an emerging molecular data source for large-scale biomedical research but inherently feature irregular sampling and informative observa…
LaT-PFN: A Joint Embedding Predictive Architecture for In-context Time-series Forecasting
Stijn Verdenius, Andrea Zerio, Roy L. M. Wang
We introduce LatentTimePFN (LaT-PFN), a foundational Time Series model with a strong embedding space that enables zero-shot forecasting. To achieve this, we perform in-context lear…