collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

Transformers learn factored representations

Adam Shai, Loren Amdahl-Culleton, Casper L. Christensen +6

Transformers pretrained via next token prediction learn to factor their world into parts, representing these factors in orthogonal subspaces of the residual stream. We formalize tw…

cs.LG2025

Rank-1 LoRAs Encode Interpretable Reasoning Signals

Jake Ward, Paul Riechers, Adam Shai

Reasoning models leverage inference-time compute to significantly enhance the performance of language models on difficult logical tasks, and have become a dominating paradigm in fr…

cs.LG2025

Constrained belief updates explain geometric structures in transformer representations

Mateusz Piotrowski, Paul M. Riechers, Daniel Filan +1

What computational structures emerge in transformers trained on next-token prediction? In this work, we provide evidence that transformers implement constrained Bayesian belief upd…

cs.LG2025

Neural networks leverage nominally quantum and post-quantum representations

Paul M. Riechers, Thomas J. Elliott, Adam S. Shai

We show that deep neural networks, including transformers and RNNs, pretrained as usual on next-token prediction, intrinsically discover and represent beliefs over 'quantum' and 'p…

cs.LG2025

Next-token pretraining implies in-context learning

Paul M. Riechers, Henry R. Bigelow, Eric A. Alt +1

We argue that in-context learning (ICL) predictably arises from standard self-supervised next-token pretraining, rather than being an exotic emergent property. This work establishe…

cs.LG2025

Transformers represent belief state geometry in their residual stream

Adam S. Shai, Sarah E. Marzen, Lucas Teixeira +2

What computational structure are we building into large language models when we train them on next-token prediction? Here, we present evidence that this structure is given by the m…