3 papers
cs.LG2026
What Do Language Priors Contribute to Darcy-Flow Inversion? A Mechanistic Audit
Taiga Saito, Yu Otake, Daijiro Mizutani +1
In ill-posed inverse problems, the recovered solution depends as much on the prior as on the data, yet much of the engineering knowledge that could serve as that prior is recorded…
cs.CE2026
TabPFN Extensions for Interpretable Geotechnical Modelling
Taiga Saito, Yu Otake, Daijiro Mizutani +1
Geotechnical site characterisation relies on sparse, heterogeneous borehole data, where uncertainty quantification and interpretability matter as much as predictive accuracy. We ev…
cs.LG2025
Tabular foundation model for GEOAI benchmark problems BM/AirportSoilProperties/2/2025
Taiga Saito, Yu Otake, Stephen Wu
This paper presents a novel application of the Tabular Prior-Data Fitted Network (TabPFN) - a transformer-based foundation model for tabular data - to geotechnical site characteriz…