arXiv:2606. 12058v1 Announce Type: cross Abstract: Attention is the key mechanism underlying in-context learning in transformers, and attention patterns have been observed empirically to emerge abruptly during training.
arXiv:2602. 19143v2 Announce Type: replace Abstract: This paper studies simple transformers trained on a high-order Markov chain, where the model must incorporate information from multiple past positions, each with different statistical importance.
arXiv:2603. 03993v2 Announce Type: replace Abstract: Multi-head attention enables transformer models to represent multiple attention patterns simultaneously.
arXiv:2512. 11784v2 Announce Type: replace Abstract: Softmax attention is a central component of transformer architectures, yet its nonlinear structure poses significant challenges for theoretical analysis.
arXiv:2606. 25010v1 Announce Type: new Abstract: Neural scaling laws for transformer language models predict smooth improvements in pretraining loss with increasing parameters, but downstream capabilities such as in-context learning are known to emerge abruptly past a certain model scale.
arXiv:2609.07086v1 Announce Type: new Abstract: Transformers are a dominant architecture in modern machine learning, powering applications across vision, language, and beyond. At the core of their su...
arXiv:2608. 09558v1 Announce Type: new Abstract: How expressive is prompting a transformer?
arXiv:2501. 18322v2 Announce Type: replace Abstract: Transformers, which are state-of-the-art in most machine learning tasks, represent the data as sequences of vectors called tokens.
arXiv:2609.39188v1 Announce Type: new Abstract: Developmental psychology holds that certain priors are given to infants prior to experience rather than induced from data, and that the influence of su...
arXiv:2508. 17821v3 Announce Type: replace-cross Abstract: This paper investigates the limitations of the normalization in attention mechanisms.
arXiv:2510. 05554v2 Announce Type: replace Abstract: As large language models scale to longer contexts, attention layers suffer from a fundamental pathology: attention scores collapse toward uniformity as context length $n$ increases, causing tokens to cluster excessively, a phenomenon known as rank-collapse.
The paper proves that deep residual self‑attention networks can universally interpolate between any two collections of sequences using only two fixed single‑head attention blocks with Gaussian‑initialized projections. The interpolation is achieved by varying the order, signs, and durations of these blocks, independent of the specific input and output sequences. The result holds for both continuous and finite depth, and the authors also extend the analysis to causal‑masked settings.
arXiv:2410. 24050v3 Announce Type: replace Abstract: Large-scale pretraining of transformers has been central to the success of foundation models.