Interval LSTM and NODE models trained with cascade or joint strategies deliver uncertainty-aware predictions for system identification via interval arithmetic.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
FiLM conditioning targeted at early message-passing layers lets pretrained GNS models generalize to new material properties using only 12 trajectories, a 5-fold data reduction versus multi-task baselines.
citing papers explorer
-
Beyond Prediction: Interval Neural Networks for Uncertainty-Aware System Identification
Interval LSTM and NODE models trained with cascade or joint strategies deliver uncertainty-aware predictions for system identification via interval arithmetic.
-
Parameter-Efficient Conditioning for Material Generalization in Graph-Based Simulators
FiLM conditioning targeted at early message-passing layers lets pretrained GNS models generalize to new material properties using only 12 trajectories, a 5-fold data reduction versus multi-task baselines.