arXiv Machine Learning

PJ-RoPE: A Fourier-Jet-Affine Position Space for Relative Attention

arXiv:2606. 05345v1 Announce Type: new Abstract: We unify RoPE's Fourier phase, Jordan-RoPE's finite jets, and ALiBi's affine recency into a single learnable relative-position space, and study which regions of this space are selected by different tasks.

arXiv AI
Jul 23

Geometric Attention: A Regime-Explicit Operator Semantics for Transformer Attention

arXiv:2601. 11618v2 Announce Type: replace-cross Abstract: Geometric Attention (GA) specifies an attention layer by four independent inputs: a finite carrier (what indices are addressable), an evidence-kernel rule (how masked proto-scores and a link induce nonnegative weights), a probe family (which observables are treated as admissible), and an anchor/update rule (which representative kernel is selected and how it is applied).

By Luis Rosario Freytes
arXiv Computation and Language
2d ago

Phase Structure in Rotary Attention: A Spectral Framework for Semantic Continuity and Execution-Boundary Governance

The paper introduces a bounded spectral framework to analyze rotary attention in transformer language models, focusing on phase alignment, hidden‑state continuity, and semantic drift. It identifies ordered hidden‑state sequences as suitable domains for spectral decomposition, derives the Rotary Position Embedding (RoPE) attention score as a sum of magnitude‑weighted cosine terms, and proves a local stability lemma linking bounded phase displacement to pre‑softmax score degradation. By defining complex modal coordinates and a weighted coherence functional, the work distinguishes representational continuity from execution‑boundary admissibility, offering a theoretical program for when spectral structure explains continuity and when external governance is required.

By Abraham Chachamovits
arXiv Machine Learning
Jun 25

Why Do Accumulated Transformations Extrapolate?

arXiv:2606. 24975v1 Announce Type: new Abstract: PaTH Attention showed that replacing RoPE's position-indexed rotations with accumulated data-dependent Householder reflections yields strong length extrapolation, though performance degrades at extreme context lengths.

By Mahesh Godavarti
arXiv Machine Learning
Sep 4

Modern Transformers Are Implicit Hybrids: From Functional Differentiation to Principled Hybrid Architecture Design

The paper proposes a principled way to design hybrid transformer architectures that combine Full Attention (FA) and Linear Attention (LA). By introducing two intervention metrics—RoPE Frequency Importance Score (RFIS) and RoPE Positional Dependence (RPD)—the authors identify a clear taxonomy of retrieval and positional heads, defining a Global Positional Band (GPBand) that aligns with training-length positional scales. Using these insights, they build a Head‑wise Hybrid Architecture (HwH) that assigns FA to global retrieval and LA to local positional modeling, achieving strong language modeling, improved retrieval, and superior zero‑shot long‑context extrapolation compared to standard Transformers and other hybrids.

By Runlin Shi, Bojian Yin, Guoqi Li
arXiv Machine Learning
Jun 24

Learning the Koopman Operator using Attention Free Transformers

arXiv:2606. 23957v1 Announce Type: new Abstract: Learning Koopman operators with autoencoders enables linear prediction in a latent space, but long-horizon rollouts often drift off the learned manifold, leading to phase and amplitude errors on systems with switching, continuous spectra, or strong transients.

By Mohammed Nagdi, Evangelos-Marios Nikolados, Alexey Yermakov, Mars Gao, Nathan Kutz, Filippo Menolascina
arXiv AI
Jul 10

Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE

arXiv:2607. 07740v1 Announce Type: cross Abstract: Modern LLMs are increasingly deployed in long-context applications such as retrieval-augmented generation, repository-level coding, and agentic workflows whose accumulated reasoning and tool traces routinely push the input an order of magnitude past the pretraining window, making zero-shot context extension the dominant deployment path for open-weight checkpoints.

By Haozhan Tang, Zerui Wang, Yuxian Gu, Song Han, Han Cai
arXiv Machine Learning
Jun 18

Attention as Frustrated Synchronization

arXiv:2606. 18694v1 Announce Type: new Abstract: A network of oscillators that synchronizes perfectly computes nothing further, so an attention architecture built from synchronization must locate its computation in structured departures from agreement.

By Joshua Nunley