Caroline Muller — accepted AI-conference papers

2026

The Perception–Physics Paradox: Probing Scientific Alignment with TC-Atlas

Dingling Yao, Andrea Polesello, Adeel Pervez, Caroline Muller, Francesco Locatello

ICML 2026poster

While Vision Foundation Models (VFMs) excel at predictive tasks on satellite imagery, their performance can arise from visual correlations rather than underlying structural invariants, making certain perception-based out-of-distribution accuracy a poor proxy for scientific utility. As a result, mode…

Cited by 0 Source ↗Scholar ↗

2024

Marrying Causal Representation Learning with Dynamical Systems for Science

Dingling Yao, Caroline Muller, Francesco Locatello

NeurIPS 2024poster

Causal representation learning promises to extend causal models to hidden causal variables from raw entangled measurements. However, most progress has focused on proving identifiability results in different settings, and we are not aware of any successful real-world application. At the same time, th…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗