arXiv Machine Learning July 23, 2026 By David R. Wessels, Farhad Ramezanghorbani, David W. Romero, Alireza Moradzadeh, Olivia Viessmann, Maksim Zhdanov, John St. John, Ken Janik, David M Knigge, Yucheng Tang, Erik J Bekkers, Saee Gopal Paliwal

Native Multi-Dimensional Subquadratic Operators via Input Dependent Long Convolutions

Read the original on arXiv Machine Learning →

arXiv:2607. 19378v1 Announce Type: new Abstract: Subquadratic alternatives to attention require compromises when applied to multi-dimensional data: standard convolutions lack global receptive fields and input dependency, while recurrent models require rasterizing data such as images, volumes, and partial differential equation (PDE) into an ad-hoc $1\rm D$ scan order that violates their spatial structure.

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

computer-vision

arXiv Machine Learning

Jun 2

Revisiting Neural Processes via Fourier Transform and Volterra Series

arXiv:2606. 01172v1 Announce Type: new Abstract: Modeling unknown latent functions from finite, irregularly sampled measurements is a recurring challenge across science and engineering.

By Peiman Mohseni, Nick Duffield, Raymond K. W. Wong

benchmarks safety

arXiv Machine Learning

Jun 2

Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders

arXiv:2606. 00746v1 Announce Type: cross Abstract: Vision foundation models are bottlenecked by the quadratic cost of self-attention, which limits usable resolution and increases the cost of large-scale pretraining.

By Yitong Jiang, Hongjun Wang, Collin McCarthy, Hanrong Ye, David Wehr, Xinhao Li, Qi Dou, Tianfan Xue, Ka Chun Cheung, Simon See, Wonmin Byeon, Ke Chen, Kai Han, Jinwei Gu, Hongxu Yin, Pavlo Molchanov, Jan Kautz, Sifei Liu

rag computer-vision efficiency multimodal

arXiv Machine Learning

Jun 15

Zero-shot generalization of transformer neural operators to larger domains

arXiv:2606. 14597v1 Announce Type: new Abstract: Transformer-based neural operators have shown remarkable performance for approximating solution operators of partial differential equations on complex geometries.

By Armand de Villeroch\'e, Sibo Cheng, Vincent Le Guen, Marc Bocquet, Rem-Sophia Mouradi, Patrick Armand, Alban Farchi, Patrick Massin

llms rag benchmarks safety

arXiv Machine Learning

Jun 5

Exact Linear Attention

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.

By Weinuo Ou

llms computer-vision reinforcement-learning efficiency safety

arXiv AI

Jul 14

Next-Dense-Stride Prediction for Multimodal Autoregressive Visual Modeling

arXiv:2607. 09892v1 Announce Type: cross Abstract: We introduce DenseAR, a new generative paradigm that reformulates autoregressive image generation as coarse-to-fine next-dense-stride prediction using a compact single-scale tokenizer.

By Chicago Y. Park, Jialin Mao, Xiaojian Xu, Taha Kass-Hout, Ulugbek S. Kamilov, Cao Xiao

diffusion computer-vision nlp multimodal

arXiv AI

Jun 16

Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality

arXiv:2505. 18227v4 Announce Type: replace-cross Abstract: In Transformer architectures, tokens\textemdash discrete units derived from raw data\textemdash are formed by segmenting inputs into fixed-length chunks.

By Zhenglun Kong, Yize Li, Fanhu Zeng, Lei Xin, Shvat Messica, Xue Lin, Pu Zhao, Manolis Kellis, Hao Tang, Marinka Zitnik

llms rag agents reinforcement-learning efficiency multimodal safety

Related stories

Revisiting Neural Processes via Fourier Transform and Volterra Series

Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders

Zero-shot generalization of transformer neural operators to larger domains

Exact Linear Attention

Next-Dense-Stride Prediction for Multimodal Autoregressive Visual Modeling

Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality