Daniel Hernandez

A probabilistic deep learning emulator for a stochastic climate model not only achieves high fidelity but also learns a latent space that unsupervisedly disentangles metastable regimes and transition dynamics.

FITTER outperforms traditional models by enabling vocabulary-agnostic inference across unseen entities and relations in temporal knowledge graphs.

Users can now exert real-time control over AI agent behaviors, seamlessly blending style with task performance in complex domains.

Predicting unseen links in knowledge graphs can often hinge on just a single half-link, revealing critical insights into model generalization.