mlsanityData to 7 Oct 2026

An Integrable Token Mixing Layer from the Generalized Yang Baxter Equation

arXiv 2606.15085 ↗First posted 13 Jun 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

The YB Mixer is a sequence token mixing layer derived from free fermion and generalized Yang Baxter structures. It applies a core principle from integrable systems where a local algebraic constraint guarantees global computational stability. By using the Ising exchange algebra the mixer creates a free fermionic structure that acts as an exactly norm preserving orthogonal map. This algebra also produces commuting transfer matrices which allow inference to be order free and adaptable to any variable budget. To ensure the model can generalize to longer sequence lengths it uses a spectral circulant generator. This generator maintains the crucial orthogonal and commuting properties of the system. The result is a highly stable and mathematically grounded architecture for sequence processing.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 41 references that are in the map. First posted on arXiv 13 Jun 2026.

Builds on

27 of 41 references.

References · 27

  1. 2017Attention Is All You Needcited by 59,932
  2. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  3. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,424
  4. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 1,979
  5. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  6. 2023RWKV: Reinventing RNNs for the Transformer Eracited by 814
  7. 2022Simplified State Space Layers for Sequence Modelingcited by 776
  8. 2013Exact solutions to the nonlinear dynamics of learning in deep linear neural networkscited by 748
  9. 2019Hamiltonian Neural Networkscited by 702
  10. 2020Long Range Arena: A Benchmark for Efficient Transformerscited by 696
  11. 2020HiPPO: Recurrent Memory with Optimal Polynomial Projectionscited by 600
  12. 2023Retentive Network: A Successor to Transformer for Large Language Modelscited by 594
15 more
  1. 2017BranchyNet: Fast Inference via Early Exiting from Deep Neural Networkscited by 591
  2. 2022On the Parameterization and Initialization of Diagonal State Space Modelscited by 418
  3. 2023Resurrecting Recurrent Neural Networks for Long Sequencescited by 397
  4. 2023Hyena Hierarchy: Towards Larger Convolutional Language Modelscited by 388
  5. 2022Confident Adaptive Language Modelingcited by 297
  6. 2015Unitary Evolution Recurrent Neural Networkscited by 291
  7. 2022Matryoshka Representation Learningcited by 268
  8. 2024Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Modelscited by 232
  9. 2019Symplectic Recurrent Neural Networkscited by 148
  10. 2017Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practicecited by 132
  11. 2016Full-Capacity Unitary Recurrent Neural Networkscited by 90
  12. 2017On orthogonality and learning recurrent networks with long term dependenciescited by 82
  13. 2017Orthogonal Recurrent Neural Networks with Scaled Cayley Transformcited by 82
  14. 2016Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNscited by 62
  15. 2016Efficient Orthogonal Parametrisation of Recurrent Neural Networks Using Householder Reflectionscited by 56

Built on by

Not cited yet.