6 papers
Does Aurora Encode Atmospheric Structure? Latent Regime Analysis and Attribution
Emma Kasteleyn, Ana Lucic
ML foundation models are able to emulate atmospheric dynamics accurately and efficiently but operate as opaque ``black boxes''. We investigate the internal representations of the A…
PhysMetrics.Weather: An Evaluation Framework for Physical Consistency in ML Weather Models
Emma Kasteleyn, Timo Maier, Axel Lauer +3
Machine learning weather prediction (MLWP) models have achieved impressive forecasting performance at a small fraction of the computational costs required for traditional physics-b…
(Sparse) Attention to the Details: Preserving Spectral Fidelity in ML-based Weather Forecasting Models
Maksim Zhdanov, Ana Lucic, Max Welling +1
We introduce Mosaic, a probabilistic weather forecasting model that addresses three failure modes of spectral degradation in ML-based weather prediction: spectral damping (statisti…
Same Content, Different Answers: Cross-Modal Inconsistency in MLLMs
Angela van Sprang, Laurens Samson, Ana Lucic +3
We introduce two new benchmarks REST and REST+ (Render-Equivalence Stress Tests) to enable systematic evaluation of cross-modal inconsistency in multimodal large language models (M…
Equivariant Sparse Autoencoders: Mechanistic Interpretability of Neural Networks on Symmetric Data
Ege Erdogan, Ana Lucic
Machine learning (ML) models achieve remarkable performance but remain hard to interpret due to their scale and complexity. In particular, their activations entangle many concepts…
A Foundation Model for the Earth System
Cristian Bodnar, Wessel P. Bruinsma, Ana Lucic +15
Reliable forecasts of the Earth system are crucial for human progress and safety from natural disasters. Artificial intelligence offers substantial potential to improve prediction…