Semidirect Fourier Delta Attention: Phase-Controlled Delta Memory with Constructive Chunk-WY Kernels
Linear attention replaces softmax attention's growing KV cache with a fixed recurrent state, but this compression limits exact state tracking and long-context memory. This paper introduces Semidirect Fourier Delta Attention (SFDA), a phase-controlled generalization of Kimi Delta Attention that replaces real diagonal decay with block-rotational Fourier control. The main result is a constructive chunk-WY factorization, enabling exact affine chunk transfer, formal stability and complexity bounds, and a compact characterization of phase-plus-low-rank memory. Experiments show SFDA learns cyclic memory while the phase-disabled KDA baseline remains near chance.
-->
[Submitted on 12 Jun 2026]
Title:Semidirect Fourier Delta Attention: Phase-Controlled Delta Memory with Constructive Chunk-WY Kernels
View a PDF of the paper titled Semidirect Fourier Delta Attention: Phase-Controlled Delta Memory with Constructive Chunk-WY Kernels, by Tiantian Zhang
View PDF HTML (experimental)
Abstract:Linear attention replaces softmax attention's growing KV cache with a fixed recurrent state, but this compression limits exact state tracking and long-context memory. We introduce \emph{Semidirect Fourier Delta Attention} (SFDA), a phase-controlled generalization of Kimi Delta Attention that replaces real diagonal decay with block-rotational Fourier control: \[ S_t=(I-\beta_t k_tk_t^*)\Lambda_tS_{t-1}+\beta_tk_tv_t^*, \qquad \Lambda_t=\diag(\alpha_t\odot e^{i\theta_t}). \] Our main result is a constructive chunk-WY factorization for products \(A_t=\Lambda_t-u_tr_t^*\), giving \[ A_t\cdots A_1=\Gamma_t-Y_tM_tW_t^* \] with rank growth bounded inside fixed chunks. This yields an exact affine chunk transfer, formal stability and complexity bounds, and a compact characterization of phase-plus-low-rank memory. We verify the algebra numerically and show in toy state-tracking experiments that SFDA learns cyclic memory where the phase-disabled KDA baseline remains near chance. Fused kernels and large-scale language-model comparisons are left to future work.
Subjects:
Machine Learning (cs.LG)
Cite as: arXiv:2607.11897 [cs.LG]
(or arXiv:2607.11897v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2607.11897
arXiv-issued DOI via DataCite
Submission history
From: Tiantian Zhang [view email] [v1] Fri, 12 Jun 2026 17:31:03 UTC (151 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Semidirect Fourier Delta Attention: Phase-Controlled Delta Memory with Constructive Chunk-WY Kernels, by Tiantian Zhang
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.LG
new | recent | 2026-07
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
IArxiv recommender toggle
IArxiv Recommender (What is IArxiv?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)