arXiv:2607. 23869v1 Announce Type: cross Abstract: Randomized features provide a scalable approximation to kernel machines, but their performance depends strongly on the choice of feature distribution.
arXiv:2606. 27748v1 Announce Type: cross Abstract: Transformer models rely on attention mechanism to capture long-range dependencies but suffer from quadratic complexity, limiting their scalability to long sequences.
The paper introduces Cubit, a Transformer‑style architecture that replaces the standard attention mechanism with Kernel Ridge Regression (KRR). By interpreting attention as Nadaraya‑Watson regression, Cubit incorporates the closed‑form KRR solution, combining kernel‑based value aggregation with normalization via the inverse kernel matrix. The authors also propose a Limited‑Range Rescale (LRR) to stabilize training and report that Cubit shows improved long‑sequence modeling, with gains increasing as training sequence length grows.
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:2606. 29256v1 Announce Type: cross Abstract: In recent years, models based on the Transformer architecture have seen widespread applications and have become one of the core tools in the field of deep learning.
arXiv:2607. 00479v1 Announce Type: new Abstract: Transformer-based large models have demonstrated remarkable generalization abilities across different tasks by leveraging a context-aware attention module for in-context learning.
arXiv:2605. 18848v3 Announce Type: replace Abstract: This paper introduces Exact Linear Attention (ELA), a mechanism that achieves linear computational complexity for Transformer attention by exploiting the exact decomposition property of kernel functions, thereby eliminating approximation error.
arXiv:2511. 05924v4 Announce Type: replace Abstract: Estimating probability density and its score from samples remains a core problem in generative modeling, Bayesian inference, and kinetic theory.
arXiv:2601.15380v2 Announce Type: replace-cross Abstract: We generalize the attention mechanism by viewing it through the lens of Entropic Optimal Transport, revealing that standard attention corresp...
Scaled dot product attention conflates directional alignment and vector magnitude, limiting its effectiveness as a similarity metric in Transformer models. We introduce L1 augmented attention, a simple and computationally parallelizable modification that subtracts a learned, head specific L1 distance between queries and keys from the dot product score.
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:2607. 18027v1 Announce Type: new Abstract: Scaled dot product attention conflates directional alignment and vector magnitude, limiting its effectiveness as a similarity metric in Transformer models.
arXiv:2608. 09558v1 Announce Type: new Abstract: How expressive is prompting a transformer?