DropsToGrid is a spatio-temporal neural process that integrates temporal sequences from noisy irregular stations with spatial radar context to produce dense stochastic rainfall fields with calibrated uncertainty, outperforming baselines even with few stations or across regions.
Neural machine translation by jointly learning to align and translate
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
PVeRA extends VeRA by making its frozen random low-rank matrices probabilistic, enabling better handling of ambiguities and outperforming prior adapters on the VTAB-1k benchmark.
citing papers explorer
-
From Drops to Grid: Noise-Aware Spatio-Temporal Neural Process for Rainfall Estimation
DropsToGrid is a spatio-temporal neural process that integrates temporal sequences from noisy irregular stations with spatial radar context to produce dense stochastic rainfall fields with calibrated uncertainty, outperforming baselines even with few stations or across regions.
-
PVeRA: Probabilistic Vector-Based Random Matrix Adaptation
PVeRA extends VeRA by making its frozen random low-rank matrices probabilistic, enabling better handling of ambiguities and outperforming prior adapters on the VTAB-1k benchmark.