arXiv Machine Learning July 24, 2026 By Boldsaikhan Bolorkhuu, Tsogtgerel Gantumur

Exact ReLU realization of affine one-dimensional refinement iterates via residual memory and offset frames

Read the original on arXiv Machine Learning →

arXiv:2607. 20586v1 Announce Type: new Abstract: We study vector-valued affine refinement operators of the form [ (W\gamma)(t)=\sum_{j\in\mathbb{Z}} A_j\gamma(Mt-j)+B(t), ] with finitely supported matrix mask and compactly supported continuous piecewise linear input and forcing data.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Aug 5

Neural network realization of binary refinement iterates via a two-chart atlas selector

arXiv:2608. 02624v1 Announce Type: cross Abstract: Refinement operators generate many functions used in wavelet constructions, subdivision schemes, and geometric modeling.

By Tsogtgerel Gantumur

arXiv Machine Learning

Jul 15

Semidirect Fourier Delta Attention: Phase-Controlled Delta Memory with Constructive Chunk-WY Kernels

arXiv:2607. 11897v1 Announce Type: new 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.

By Tiantian Zhang

efficiency

arXiv Machine Learning

Jul 28

When Can Depth Replace Precision? A Resource Theory of Quantized Neural Computation

arXiv:2607. 23390v1 Announce Type: new Abstract: When can additional low-bit residual computation replace missing numerical precision for a fixed input-output map?

By Mojtaba Soltanalian

efficiency

arXiv Machine Learning

Jul 30

A Compositional Theory of Causally Masked Transformers

arXiv:2607. 26988v1 Announce Type: cross Abstract: What types of decision problems can a causally masked, finite-precision transformer solve for inputs of arbitrary length?

By Franz Nowak, Ryan Cotterell, Reda Boumasmoud

llms rag

arXiv Machine Learning

Jun 9

Families of Control-Cost-Parametrized Inverse-Optimal Universal Stabilizers

arXiv:2606. 09047v1 Announce Type: cross Abstract: A classical universal stabilization formula offers the practitioner no design freedom: it is a single, parameter-free object.

By Miroslav Krstic, Luke Bhan

arXiv Machine Learning

Aug 6

Training Crossroads for Recurrent Vision Transformers: Recurrence, Neural ODEs, and Deep Supervision

arXiv:2608. 04879v1 Announce Type: new Abstract: Vision Transformers (ViTs) achieve strong image-recognition performance, but their parameter count grows linearly with depth when each block is independently parameterized.

By Grzegorz Gruszczynski, Pawel Olszowiec, Michal Byra, Grzegorz Stefanski, Alberto Presta

llms safety

Related stories

Neural network realization of binary refinement iterates via a two-chart atlas selector

Semidirect Fourier Delta Attention: Phase-Controlled Delta Memory with Constructive Chunk-WY Kernels

When Can Depth Replace Precision? A Resource Theory of Quantized Neural Computation

A Compositional Theory of Causally Masked Transformers

Families of Control-Cost-Parametrized Inverse-Optimal Universal Stabilizers

Training Crossroads for Recurrent Vision Transformers: Recurrence, Neural ODEs, and Deep Supervision