Cover Image

Bilinear autoencoders find interpretable manifolds

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dooms, Thomas, Gauderis, Ward, Wiggins, Geraint, Oramas, Jose
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Compositionality Unlocks Deep Interpretable Models
by: Dooms, Thomas, et al.
Published: (2025)

Finding Manifolds With Bilinear Autoencoders
by: Dooms, Thomas, et al.
Published: (2025)

From Mechanistic to Compositional Interpretability
by: Gauderis, Ward, et al.
Published: (2026)

Bilinear MLPs enable weight-based mechanistic interpretability
by: Pearce, Michael T., et al.
Published: (2024)

Weight-based Decomposition: A Case for Bilinear MLPs
by: Pearce, Michael T., et al.
Published: (2024)

Quantum Methods for Managing Ambiguity in Natural Language Processing
by: Eisinger, Jurek, et al.
Published: (2025)

Tokenized SAEs: Disentangling SAE Reconstructions
by: Dooms, Thomas, et al.
Published: (2025)

BioOSS: A Bio-Inspired Oscillatory State System with Spatio-Temporal Dynamics
by: Yuan, Zhongju, et al.
Published: (2025)

Towards a Formal Creativity Theory: Preliminary results in Novelty and Transformativeness
by: Santo, Luís Espírito, et al.
Published: (2024)

A novel Reservoir Architecture for Periodic Time Series Prediction
by: Yuan, Zhongju, et al.
Published: (2024)

Fractals made Practical: Denoising Diffusion as Partitioned Iterated Function Systems
by: Dooms, Ann
Published: (2026)

Understanding sparse autoencoder scaling in the presence of feature manifolds
by: Michaud, Eric J., et al.
Published: (2025)

Efficient Post-Hoc Uncertainty Calibration via Variance-Based Smoothing
by: Denoodt, Fabian, et al.
Published: (2025)

Can sparse autoencoders be used to decompose and interpret steering vectors?
by: Mayne, Harry, et al.
Published: (2024)

Towards the Characterization of Representations Learned via Capsule-based Network Architectures
by: Tawalbeh, Saja, et al.
Published: (2023)

Why should autoencoders work?
by: Kvalheim, Matthew D., et al.
Published: (2023)

Slim multi-scale convolutional autoencoder-based reduced-order models for interpretable features of a complex dynamical system
by: Teutsch, Philipp, et al.
Published: (2025)

Deep Model Interpretation with Limited Data : A Coreset-based Approach
by: Behzadi-Khormouji, Hamed, et al.
Published: (2024)

When Are Two Networks the Same? Tensor Similarity for Mechanistic Interpretability
by: Gonzalez, ML Nissen, et al.
Published: (2026)

scMEDAL for the interpretable analysis of single-cell transcriptomics data with batch effect visualization using a deep mixed effects autoencoder
by: Andrade, Aixa X., et al.
Published: (2024)

Matching aggregate posteriors in the variational autoencoder
by: Saha, Surojit, et al.
Published: (2023)

Preserving Bilinear Weight Spectra with a Signed and Shrunk Quadratic Activation Function
by: Abohwo, Jason, et al.
Published: (2025)

Smooth InfoMax -- Towards Easier Post-Hoc Interpretability
by: Denoodt, Fabian, et al.
Published: (2024)

Complex variational autoencoders admit Kähler structure
by: Gracyk, Andrew
Published: (2025)

Scaling and evaluating sparse autoencoders
by: Gao, Leo, et al.
Published: (2024)

Variational Bayes image restoration with compressive autoencoders
by: Biquard, Maud, et al.
Published: (2023)

Bilinear Input Modulation for Mamba: Koopman Bilinear Forms for Memory Retention and Multiplicative Computation
by: Fujii, Hiroki, et al.
Published: (2026)

Decomposing multimodal embedding spaces with group-sparse autoencoders
by: Kaushik, Chiraag, et al.
Published: (2026)

Adaptive sampling using variational autoencoder and reinforcement learning
by: Rasheed, Adil, et al.
Published: (2025)

Bilinear Coordinate Alignment for Training-Free Task-Vector Transfer
by: Son, Jungyong, et al.
Published: (2026)

Structural Disentanglement in Bilinear MLPs via Architectural Inductive Bias
by: Nema, Ojasva, et al.
Published: (2026)

Tractable Instances of Bilinear Maximization: Implementing LinUCB on Ellipsoids
by: Zhang, Raymond, et al.
Published: (2025)

Graph Structure Inference with BAM: Introducing the Bilinear Attention Mechanism
by: Froehlich, Philipp, et al.
Published: (2024)

Bilinear Convolution Decomposition for Causal RL Interpretability
by: Oozeer, Narmeen, et al.
Published: (2024)

Global atmospheric data assimilation with multi-modal masked autoencoders
by: Vandal, Thomas J., et al.
Published: (2024)

Investigating task-specific prompts and sparse autoencoders for activation monitoring
by: Tillman, Henk, et al.
Published: (2025)

Neuc-MDS: Non-Euclidean Multidimensional Scaling Through Bilinear Forms
by: Deng, Chengyuan, et al.
Published: (2024)

DANAE: a denoising autoencoder for underwater attitude estimation
by: Russo, Paolo, et al.
Published: (2020)

Comba: Improving Bilinear RNNs with Closed-loop Control
by: Hu, Jiaxi, et al.
Published: (2025)

Theoretically informed selection of latent activation in autoencoder based recommender systems
by: Susman, Aviad
Published: (2024)