Cover Image

Transformers learn factored representations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shai, Adam, Amdahl-Culleton, Loren, Christensen, Casper L., Bigelow, Henry R., Rosas, Fernando E., Boyd, Alexander B., Alt, Eric A., Ray, Kyle J., Riechers, Paul M.
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

Next-token pretraining implies in-context learning
by: Riechers, Paul M., et al.
Published: (2025)

Neural networks leverage nominally quantum and post-quantum representations
by: Riechers, Paul M., et al.
Published: (2025)

The Observer Effect in World Models: Invasive Adaptation Corrupts Latent Physics
by: Internò, Christian, et al.
Published: (2026)

Constrained belief updates explain geometric structures in transformer representations
by: Piotrowski, Mateusz, et al.
Published: (2025)

Rank-1 LoRAs Encode Interpretable Reasoning Signals
by: Ward, Jake, et al.
Published: (2025)

Thermodynamic Advantage of Quantum Time-Reversal
by: Boyd, Alexander B., et al.
Published: (2025)

Transformers represent belief state geometry in their residual stream
by: Shai, Adam S., et al.
Published: (2024)

Large Interconnected Thermodynamic Systems Nearly Minimize Entropy Production
by: Ray, Kyle J., et al.
Published: (2025)

Decomposition of Small Transformer Models
by: Christensen, Casper L., et al.
Published: (2025)

O homem e a gente: intercomunicação humana de Ortega y Gasset, traduzido por José Carlos Lisboa. 2ª edição. Rio de Janeiro: Livro Ibero-Americano, 1973. 306 pp
by: José Guillermo Culleton
Published: (2005)

O ordenamento moral e o ius naturae em Duns Scotus
by: Alfredo Santiago Culleton
Published: (2008)

AI in a vat: Fundamental limits of efficient world modelling for agent sandboxing and interpretability
by: Rosas, Fernando, et al.
Published: (2025)

Geometry and Dynamics of LayerNorm
by: Riechers, Paul M.
Published: (2024)

Lactate Threshold Testing In Collegiate Nordic Skiers: Pilot Study
by: Nathan Nuengchana, et al.
Published: (2025)

A new approach to the $SL_n$ spider
by: Bigelow, Stephen
Published: (2018)

Robust, wirtschaftlich, nachhaltig – die Zukunft der Eisenbahnbrücken
by: Hetty Bigelow
Published: (2025)

A Portrait of 30 Years.
by: Riechers, Maggie
Published: (1995)

Bi-Axial Transformers: Addressing the Increasing Complexity of EHR Classification
by: DeVries, Rachael, et al.
Published: (2025)

Welch, Bigelow, & Co. May 12, 1875
by: Welch, Bigelow & Co.
Published: (1875)

Menacing Environments
by: Bigelow, Benjamin A.
Published: (2023)

Cuker, B. E. (Editor) 2020. Diet for a Sustainable Ecosystem: The Science for Recovering the Health of the Chesapeake Bay and its People. Springer. ISBN 978‐3‐030‐45480‐7. XIV, 430 p
by: Camryn Leigh Bigelow
Published: (2025)

Neuradicon: operational representation learning of neuroimaging reports
by: Watkins, Henry, et al.
Published: (2021)

Identifiability and minimality bounds of quantum and post-quantum models of classical stochastic processes
by: Riechers, Paul M., et al.
Published: (2025)

Utopie
by: Riechers, Hans-Christian
Published: (2024)

Do Unusually Cold Starburst Galaxies Exist? A Case Study
by: Riechers, Dominik A.
Published: (2024)

Laguna bélgica : patrimonio natural e interpretación ambiental / Alejandra Riechers Pérez, José Eduardo Morales-Pérez, Efraín Hern ndez García compiladores
by: Riechers Pérez A
Published: (2009)

Registros de Choeronycteris mexicana (Chiroptera: Phyllostomidae) en Chiapas
by: Alejandra Riechers-Pérez
Published: (2009)

Análisis mastofaunístico de la Zona Sujeta a Conservación Ecológica Laguna Bélgica, Chiapas, México
by: Alejandra Riechers PÉREZ
Published: (2004)

Análisis mastofaunístico de la Zona Sujeta a Conservación Ecológica Laguna Bélgica, Chiapas, México
by: Alejandra Riechers PÉREZ
Published: (2004)

Consumo de polen de una colonia de maternidad de Leptonycteris curasoae yerbabuenae en Tuxtla Gutiérrez, Chiapas, México.
by: Alejandra Riechers PÉREZ
Published: (2003)

From monoliths to modules: Decomposing transducers for efficient world modelling
by: Boyd, Alexander, et al.
Published: (2025)

Forking Paths in Neural Text Generation
by: Bigelow, Eric, et al.
Published: (2024)

Quantum groups from homologies of configuration spaces
by: Bigelow, Stephen, et al.
Published: (2024)

Library and Information Services for Native Americans.
by: Bigelow, Jane M. H.
Published: (1994)

Functional Plan for the Illinois Library Telecommunications Network.
by: Bigelow, Linda, et al.
Published: (1989)

Community College Learning Resources Centers at the Crossroads: Illinois, a Case Study.
by: Dubin, Eileen, et al.
Published: (1986)

Chain of Time: In-Context Physical Simulation with Image Generation Models
by: Wang, YingQiao, et al.
Published: (2025)

Are language models aware of the road not taken? Token-level uncertainty and hidden state dynamics
by: Zur, Amir, et al.
Published: (2025)

Seeding establishment from one- and two-seeded fruits of Cryptantha flava : a test of parent-offspring conflict
by: Casper, B.B
Published: (1990)

Evidence for selective embryo abortion in Cryptantha flava
by: Casper, B.B
Published: (1981)