Tag
This paper introduces DMDIntel, a method that uses dynamic mode decomposition to make LLM predictions interpretable by decomposing hidden states into modes and ranking token attributions, outperforming existing techniques like PCA, integrated gradients, and SHAP.
This paper introduces dynamics-aware preprocessing via Koopman-based upsampling (DMD/EDMD) to improve derivative estimation and equation discovery from sparse, noisy data, benchmarking on ODE and PDE systems.
This paper introduces SpatioTemporal Causal Network Diagnostics (ST-CND), a framework that uses data-driven causal networks and dynamic mode decomposition to provide localized early warning of geographic tipping points, outperforming classical spatial indicators on synthetic and observational benchmarks.