Papers for
transformer model developers
Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.
Transformer attention gating shapes how representations shrink or grow
Anisotropic Representation Dynamics in Transformers
Abstract: Small differences between internal representations can shrink or grow as they pass through a Transformer layer, affecting how information is preserved and how sensitive the model is to perturbations. Yet it remains unclear when changes in attention weights can turn a representation difference that would otherwise shrink into one that grows. We develop a \textbf{Mixture-Gated Theory of Anisotropic Representation Dynamics} that separates self-attention into value transport, query gating, and key gating. Our analysis reveals how the geometry of attended representations constrains gating and how interactions between these mechanisms can reverse contraction induced by value transport. We formalize this phenomenon as gating-induced regime switching, where a representation difference contracts under fixed attention routing but expands under full attention. We derive a necessary and sufficient spectral criterion that certifies the existence or absence of switching and identifies switching directions without exhaustive search. Beyond existence, our theory characterizes maximum relative switching strength, certifies the severity of contraction that gating can overcome, and determines the largest dimension of a subspace in which every nonzero direction switches. Experiments across four Transformer architectures validate these predictions through analytical and finite-forward comparisons, revealing distinct and joint query--key gating mechanisms and nontrivial switching subspaces. Our results provide a mechanistic and spectral understanding of how attention routing can alter local representation dynamics.
Transformer attention equality condition holds widely in popular AI models
An equality condition for the Dobrushin bound on attention rollout and how often it holds in trained transformers
Abstract: The Dobrushin coefficient of each attention-rollout factor satisfies $κ(\frac12(I+A))\le\frac12(1+κ(A))$, and multiplying these inequalities over layers bounds the coefficient of the whole rollout. We characterise exactly when the layerwise bound is tight: equality holds if and only if some token pair attaining $κ(A)$ is mutually self-dominant - each of the two attends to itself at least as strongly as the other attends to it. The condition is far from automatic: uniformly random stochastic matrices satisfy it only 24-30% of the time. When tested on the head-averaged attention of each individual input and restricted to content tokens - image patches, words or tabular features, excluding cls, register and separator tokens - the condition holds for essentially every input at every layer of DINOv2 (three model sizes), RoBERTa and DistilBERT. In the supervised models DeiT-B and ViT-B/16 it holds for 91% and 64% of input-layer pairs respectively, with all failures occurring late in depth. In FT-Transformer trained on two standard tabular benchmarks it holds for only 11-44% of input-layer pairs. The special tokens account for almost all failures in DINOv2 and the language models: when they are included, the condition holds for only 82-97% of input-layer pairs.