4 papers
Encrypt What Matters: When Selective Homomorphic Inference Is Efficient
Ali Backour, Juan Reyes, Jaime Punyed +1
Fully homomorphic encryption (FHE) enables inference on private data without revealing it to the server, but evaluating an entire input under FHE is expensive. We study \emph{selec…
The Dynamics of Continuous Mixture Collapse in Language Models
Ali Backour
LLMs latent-state reasoning methods replace discrete intermediate tokens with continuous states, such as weighted mixtures of token embeddings, to retain multiple possible reasonin…
Turbulence teaches equivariance to neural networks
Ryley McConkey, Julia Balla, Jeremiah Bailey +5
We show that the rotational nature of turbulence affects how neural networks learn mappings between quantities governed by the Navier-Stokes equations. We train super-resolution mo…
Implicit Augmentation from Distributional Symmetry in Turbulence Super-Resolution
Julia Balla, Jeremiah Bailey, Ali Backour +4
The immense computational cost of simulating turbulence has motivated the use of machine learning approaches for super-resolving turbulent flows. A central challenge is ensuring th…