arXiv Machine Learning June 16, 2026 By Leyla Naz Candogan, Arshia Afzal, Pol Puigdemont, Volkan Cevher

Spatial Priors via Space Filling Curves for Small and Limited Data Vision Transformers

Read the original on arXiv Machine Learning →

arXiv:2606. 14757v1 Announce Type: cross Abstract: Though Vision Transformers (ViTs) have become the dominant backbone in many computer vision tasks, due to permutation equivariance, their attention mechanism lacks explicit spatial inductive biases.

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

arXiv AI

Jun 30

ScAle: Attention Head Scaling as a Minimal Adapter for Spatial Reasoning in Vision Language Models

arXiv:2606. 29579v1 Announce Type: cross Abstract: Spatial reasoning remains a persistent challenge for many vision language models (VLMs), and improving it typically requires fine-tuning with substantial additional parameters.

By Rahul Chowdhury, Timothy A Rupprecht, Xuan Shen, Pu Zhao, Yanzhi Wang

llms fine-tuning benchmarks

arXiv Machine Learning

Jun 4

Spatially Grounded Concept Bottleneck Models via Part-Factorized Attention

arXiv:2606. 04364v1 Announce Type: cross Abstract: Concept bottleneck models (CBMs) predict a layer of human-named attributes before predicting a class, which makes their decisions auditable.

By Dhanesh Ramachandram

llms computer-vision

Hugging Face Trending Papers

Aug 11

Grid-Preserving Knowledge Distillation: Transferring Convolutional Inductive Bias to Vision Transformers under Data Scarcity

Vision Transformers underperform convolutional networks when training data is scarce, and distilling convolutional inductive biases from a CNN teacher is an effective remedy that leaves the deployed model unchanged. General-purpose feature distillation, however, transfers little in this setting.

llms efficiency benchmarks safety

arXiv AI

Jun 6

HiDe: Rethinking The Zoom-IN method in High Resolution MLLMs via Hierarchical Decoupling

arXiv:2510. 00054v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have made significant strides in visual understanding tasks.

By Xianjie Liu, Yiman Hu, Yixiong Zou, Liang Wu, Jian Xu, Bo Zheng

llms reinforcement-learning multimodal benchmarks safety

arXiv AI

Jun 4

Selective Coupling of Decoupled Informative Regions: Masked Attention Alignment for Data-Free Quantization of Vision Transformers

arXiv:2606. 04373v1 Announce Type: cross Abstract: Data-Free Quantization (DFQ) addresses data security concerns by synthesizing samples, without accessing real data.

By Biao Qian, Yang Wang, Yong Wu, Jungong Han

llms efficiency benchmarks safety

arXiv Machine Learning

Jun 29

Prism Transformer: Progressive Head Schedules for Hierarchical Attention Processing

arXiv:2606. 27449v1 Announce Type: new Abstract: Multi-head attention conventionally partitions the hidden dimension equally across all heads at every layer, enforcing an identical representational subspace dimension (dh = dmodel/h) throughout the models depth.

By Shubham Aggarwal

llms benchmarks

Related stories

ScAle: Attention Head Scaling as a Minimal Adapter for Spatial Reasoning in Vision Language Models

Spatially Grounded Concept Bottleneck Models via Part-Factorized Attention

Grid-Preserving Knowledge Distillation: Transferring Convolutional Inductive Bias to Vision Transformers under Data Scarcity

HiDe: Rethinking The Zoom-IN method in High Resolution MLLMs via Hierarchical Decoupling

Selective Coupling of Decoupled Informative Regions: Masked Attention Alignment for Data-Free Quantization of Vision Transformers

Prism Transformer: Progressive Head Schedules for Hierarchical Attention Processing