Image de couverture de livre

Decomposing multimodal embedding spaces with group-sparse autoencoders

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kaushik, Chiraag, Barch, Davis, Fanelli, Andrea
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Insights into a radiology-specialised multimodal large language model with sparse autoencoders
par: Bouzid, Kenza, et autres
Publié: (2025)

Precise asymptotics of reweighted least-squares algorithms for linear diagonal networks
par: Kaushik, Chiraag, et autres
Publié: (2024)

A general technique for approximating high-dimensional empirical kernel matrices
par: Kaushik, Chiraag, et autres
Publié: (2025)

Scaling and evaluating sparse autoencoders
par: Gao, Leo, et autres
Publié: (2024)

The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective
par: Lin, Chi-Heng, et autres
Publié: (2022)

Understanding sparse autoencoder scaling in the presence of feature manifolds
par: Michaud, Eric J., et autres
Publié: (2025)

Investigating task-specific prompts and sparse autoencoders for activation monitoring
par: Tillman, Henk, et autres
Publié: (2025)

Applying sparse autoencoders to unlearn knowledge in language models
par: Farrell, Eoin, et autres
Publié: (2024)

Steering CLIP's vision transformer with sparse autoencoders
par: Joseph, Sonia, et autres
Publié: (2025)

Pairwise matrices for sparse autoencoders: single-feature inspection mislabels causal axes
par: Riegler, Michael A., et autres
Publié: (2026)

Can sparse autoencoders make sense of gene expression latent variable models?
par: Schuster, Viktoria
Publié: (2024)

Pre-trained Tabular Foundation Models as Versatile Summary Networks for Neural Posterior Estimation
par: Pickens, Elliot, et autres
Publié: (2026)

Can sparse autoencoders be used to decompose and interpret steering vectors?
par: Mayne, Harry, et autres
Publié: (2024)

Transformer autoencoder with local attention for sparse and irregular time series with application on risk estimation
par: Rodis, Panteleimon
Publié: (2026)

A multimodal dynamical variational autoencoder for audiovisual speech representation learning
par: Sadok, Samir, et autres
Publié: (2023)

Discretization of continuous input spaces in the hippocampal autoencoder
par: Amil, Adrian F., et autres
Publié: (2024)

The role of data embedding in quantum autoencoders for improved anomaly detection
par: Araz, Jack Y., et autres
Publié: (2024)

Introducing a microstructure-embedded autoencoder approach for reconstructing high-resolution solution field data from a reduced parametric space
par: Koopas, Rasoul Najafi, et autres
Publié: (2024)

Decomposing Prediction Mechanisms for In-Context Recall
par: Daniels, Sultan, et autres
Publié: (2025)

Inferring stability properties of chaotic systems on autoencoders' latent spaces
par: Özalp, Elise, et autres
Publié: (2024)

Balanced Data, Imbalanced Spectra: Unveiling Class Disparities with Spectral Imbalance
par: Kaushik, Chiraag, et autres
Publié: (2024)

New Equivalences Between Interpolation and SVMs: Kernels and Structured Features
par: Kaushik, Chiraag, et autres
Publié: (2023)

SELECTOR: Heterogeneous graph network with convolutional masked autoencoder for multimodal robust prediction of cancer survival
par: Pan, Liangrui, et autres
Publié: (2024)

Why should autoencoders work?
par: Kvalheim, Matthew D., et autres
Publié: (2023)

Mori-Zwanzig latent space Koopman closure for nonlinear autoencoder
par: Gupta, Priyam, et autres
Publié: (2023)

DashCLIP: Leveraging multimodal models for generating semantic embeddings for DoorDash
par: Gurjar, Omkar, et autres
Publié: (2025)

Generative Distribution Embeddings: Lifting autoencoders to the space of distributions for multiscale representation learning
par: Fishman, Nic, et autres
Publié: (2025)

Bilinear autoencoders find interpretable manifolds
par: Dooms, Thomas, et autres
Publié: (2026)

Matching aggregate posteriors in the variational autoencoder
par: Saha, Surojit, et autres
Publié: (2023)

Ensemble Kalman filter in latent space using a variational autoencoder pair
par: Pasmans, Ivo, et autres
Publié: (2025)

Complex variational autoencoders admit Kähler structure
par: Gracyk, Andrew
Publié: (2025)

Fault detection and diagnosis for the engine electrical system of a space launcher based on a temporal convolutional autoencoder and calibrated classifiers
par: Basora, Luis, et autres
Publié: (2025)

Adaptive sampling using variational autoencoder and reinforcement learning
par: Rasheed, Adil, et autres
Publié: (2025)

Decomposable Neuro Symbolic Regression
par: Morales, Giorgio, et autres
Publié: (2025)

Decomposable Transformer Point Processes
par: Panos, Aristeidis
Publié: (2024)

PepCompass: Navigating peptide embedding spaces using Riemannian Geometry
par: Możejko, Marcin, et autres
Publié: (2025)

Causal and Federated Multimodal Learning for Cardiovascular Risk Prediction under Heterogeneous Populations
par: Kaushik, Rohit, et autres
Publié: (2026)

An attempt to generate new bridge types from latent space of variational autoencoder
par: Zhang, Hongjun
Publié: (2023)

DANAE: a denoising autoencoder for underwater attitude estimation
par: Russo, Paolo, et autres
Publié: (2020)

Sailing in high-dimensional spaces: Low-dimensional embeddings through angle preservation
par: Fischer, Jonas, et autres
Publié: (2024)