8 papers
Beyond Uniform Local Isometry and Topology: FactoMap for Disentangled Representations
Sohini Gupta, Bahareh Tolooshams
Many disentanglement methods represent generative factors using Euclidean product coordinates, although the underlying factor spaces may wrap, collapse, or have position-dependent…
Mechanistic Interpretability with Sparse Autoencoder Neural Operators
Bahareh Tolooshams, Ailsa Shen, Anima Anandkumar
We introduce sparse autoencoder neural operators (SAE-NOs), a new class of sparse autoencoders that operate in function spaces rather than fixed-dimensional Euclidean representatio…
EquiReg: Equivariance Regularized Diffusion for Inverse Problems
Bahareh Tolooshams, Aditi Chandrashekar, Rayhan Zirvi +4
Diffusion models represent the state-of-the-art for solving inverse problems such as image restoration tasks. Diffusion-based inverse solvers incorporate a likelihood term to guide…
NOBLE -- Neural Operator with Biologically-informed Latent Embeddings to Capture Experimental Variability in Biological Neuron Models
Luca Ghafourpour, Valentin Duruisseaux, Bahareh Tolooshams +3
Characterizing the cellular properties of neurons is fundamental to understanding their function in the brain. In this quest, the generation of bio-realistic models is central towa…
Fourier Neural Operators for Learning Dynamics in Quantum Spin Systems
Freya Shah, Taylor L. Patti, Julius Berner +3
Fourier Neural Operators (FNOs) excel on tasks using functional data, such as those originating from partial differential equations. Such characteristics render them an effective a…
A Unified Model for Compressed Sensing MRI Across Undersampling Patterns
Armeet Singh Jatyani, Jiayun Wang, Aditi Chandrashekar +4
Compressed Sensing MRI reconstructs images of the body's internal anatomy from undersampled measurements, thereby reducing scan time. Recently, deep learning has shown great potent…