Cover Image

fmxcoders: Factorized Masked Crosscoders for Cross-Layer Feature Discovery

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Demou, Andreas D., Koromilas, Panagiotis, Oldfield, James, Panagakis, Yannis, Nicolaou, Mihalis A.
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

PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decoding
by: Koromilas, Panagiotis, et al.
Published: (2026)

Neural Collapse by Design: Learning Class Prototypes on the Hypersphere
by: Koromilas, Panagiotis, et al.
Published: (2026)

Bridging Mini-Batch and Asymptotic Analysis in Contrastive Learning: From InfoNCE to Kernel-Based Losses
by: Koromilas, Panagiotis, et al.
Published: (2024)

A Principled Framework for Multi-View Contrastive Learning
by: Koromilas, Panagiotis, et al.
Published: (2025)

Environment-Aware Satellite Image Generation with Diffusion Models
by: Kostagiolas, Nikos, et al.
Published: (2025)

Enabling Local Editing in Diffusion Models by Joint and Individual Component Analysis
by: Kouzelis, Theodoros, et al.
Published: (2024)

Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization
by: Oldfield, James, et al.
Published: (2024)

Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders
by: Oldfield, James, et al.
Published: (2025)

Cross-Architecture Model Diffing with Crosscoders: Unsupervised Discovery of Differences Between LLMs
by: Jiralerspong, Thomas, et al.
Published: (2026)

Generalization analysis of an unfolding network for analysis-based Compressed Sensing
by: Kouni, Vicky, et al.
Published: (2023)

Metanetworks as Regulatory Operators: Learning to Edit for Requirement Compliance
by: Kalogeropoulos, Ioannis, et al.
Published: (2025)

Scale Equivariant Graph Metanetworks
by: Kalogeropoulos, Ioannis, et al.
Published: (2024)

Delta-Crosscoder: Robust Crosscoder Model Diffing in Narrow Fine-Tuning Regimes
by: Kassem, Aly, et al.
Published: (2026)

Group Crosscoders for Mechanistic Analysis of Symmetry
by: Gorton, Liv
Published: (2024)

Exposing Hidden Biases in Text-to-Image Models via Automated Prompt Search
by: Plitsis, Manos, et al.
Published: (2025)

Audio-visual video-to-speech synthesis with synthesized input audio
by: Kefalas, Triantafyllos, et al.
Published: (2023)

Large-scale unsupervised audio pre-training for video-to-speech synthesis
by: Kefalas, Triantafyllos, et al.
Published: (2023)

Sparse Crosscoders for diffing MoEs and Dense models
by: Chaudhari, Marmik, et al.
Published: (2026)

Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning
by: Minder, Julian, et al.
Published: (2025)

Language Models are Injective and Hence Invertible
by: Nikolaou, Giorgos, et al.
Published: (2025)

Advancing Brainwave Modeling with a Codebook-Based Foundation Model
by: Barmpas, Konstantinos, et al.
Published: (2025)

Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining
by: Bayazit, Deniz, et al.
Published: (2025)

Are Large Brainwave Foundation Models Capable Yet? Insights from Fine-tuning
by: Lee, Na, et al.
Published: (2025)

Binary Feature Mask Optimization for Feature Selection
by: Lorasdagi, Mehmet E., et al.
Published: (2024)

Revisiting Pre-processing Group Fairness: A Modular Benchmarking Framework
by: Oldfield, Brodie, et al.
Published: (2025)

Benchmarking Counterfactual Image Generation
by: Melistas, Thomas, et al.
Published: (2024)

Beyond Linear Probes: Dynamic Safety Monitoring for Language Models
by: Oldfield, James, et al.
Published: (2025)

Bikelution: Federated Gradient-Boosting for Scalable Shared Micro-Mobility Demand Forecasting
by: Tziorvas, Antonios, et al.
Published: (2026)

On the Role of Attention Masks and LayerNorm in Transformers
by: Wu, Xinyi, et al.
Published: (2024)

Cross-Layer Discrete Concept Discovery for Interpreting Language Models
by: Garg, Ankur, et al.
Published: (2025)

On the hydrodynamic behaviour of the immersed boundary -- lattice Boltzmann method for wetting problems
by: Bellantoni, Elisa, et al.
Published: (2026)

Linear Transformer Topological Masking with Graph Random Features
by: Reid, Isaac, et al.
Published: (2024)

Unsupervised Neighborhood Propagation Kernel Layers for Semi-supervised Node Classification
by: Achten, Sonny, et al.
Published: (2023)

FLP-XR: Future Location Prediction on Extreme Scale Maritime Data in Real-time
by: Theodoropoulos, George S., et al.
Published: (2025)

On Electric Vehicle Energy Demand Forecasting and the Effect of Federated Learning
by: Tritsarolis, Andreas, et al.
Published: (2026)

StackFeat RL: Reinforcement Learning over Iterative Dual Criterion Feature Selection for Stable Biomarker Discovery
by: Yermekov, A., et al.
Published: (2026)

An Item Response Theory-based R Module for Algorithm Portfolio Analysis
by: Oldfield, Brodie, et al.
Published: (2024)

Dynamic Features Adaptation in Networking: Toward Flexible training and Explainable inference
by: Belkhiter, Yannis, et al.
Published: (2025)

Morphology-Aware Peptide Discovery via Masked Conditional Generative Modeling
by: Costa, Nuno, et al.
Published: (2025)

Cross-domain Open-world Discovery
by: Wen, Shuo, et al.
Published: (2024)