A drop-in Gaussian Mixture Model output layer converts deterministic traffic models to multi-modal probabilistic predictors trained solely with negative log-likelihood loss.
, author Shazeer, N
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
A framework using language models to simulate non-existent experiments and derive novel testable hypotheses on dative verb acquisition and cross-structural generalization in children.
citing papers explorer
-
Unveiling Stochasticity: Universal Multi-modal Probabilistic Modeling for Traffic Forecasting
A drop-in Gaussian Mixture Model output layer converts deterministic traffic models to multi-modal probabilistic predictors trained solely with negative log-likelihood loss.
-
A systematic framework for generating novel experimental hypotheses from language models
A framework using language models to simulate non-existent experiments and derive novel testable hypotheses on dative verb acquisition and cross-structural generalization in children.