arXiv Machine Learning June 9, 2026 By O\u{g}uzhan Ercan

Phase Marginalization for Patch-Grid Instability in Vision Transformers

Read the original on arXiv Machine Learning →

arXiv:2606. 08132v1 Announce Type: cross Abstract: Vision Transformers operate on fixed patch grids, which can introduce phase-dependent instability for dense prediction: changing the patch partition can change the token evidence available to a pixel, especially near boundaries.

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

arXiv Machine Learning

Jul 31

MixFrag: Fragility-Guided Mixed-Precision Post-Training Quantization for Vision Transformers

arXiv:2607. 28589v1 Announce Type: cross Abstract: Post-training quantization (PTQ) has emerged as an effective solution for deploying Vision Transformers (ViTs) on resource-constrained devices.

By Md. Mehrab Hossain Opi, Robiul Islam Ryad, Md. Umar Faruk

llms computer-vision efficiency benchmarks

Hugging Face Trending Papers

Jun 16

RegimeVGGT: Layer-Wise Spatially Preserving Redundancy Removal for Visual Geometry Grounded Transformer

Visual Geometry Grounded Transformer (VGGT) recovers dense 3D scene structure from multi-view images in one forward pass, but quadratic cross-frame attention limits its scalability. Existing training-free accelerators reduce computation uniformly along one axis, missing layer heterogeneity.

llms safety

arXiv AI

Jul 7

Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers

arXiv:2607. 02612v1 Announce Type: cross Abstract: Vision Transformers achieve strong image classification accuracy but process all image regions with nearly the same computation, even when many regions are redundant or uninformative.

By Aravind Pradeep, Samira Nazari, Mahdi Taheri, Christian Herglotz

llms computer-vision efficiency benchmarks

arXiv AI

1d ago

X$^2$Localizer: Cross-grained Alignment for Progressive Cross-view Video Geo-localization

arXiv:2608. 16658v1 Announce Type: cross Abstract: Cross-view Video Geo-localization (CVG) aims to localize ground-view videos by retrieving their corresponding geo-tagged aerial images.

By Zichao Zeng, Weijia Fan, Yufan Chen, June Moh Goo, Junwei Zheng, Ruiping Liu, Kunyu Peng, Jiaming Zhang, Rainer Stiefelhagen, Jan Boehm

benchmarks safety

arXiv AI

Aug 12

Cross-View Sequential Visual Localization with Spatio-Temporal Context Modeling for Autonomous Driving

arXiv:2608. 10660v1 Announce Type: cross Abstract: Continuous and reliable localization is essential for autonomous driving.

By Jiaping Wang, Shaobo Li, Zhen Wang

agents robotics fine-tuning benchmarks

arXiv AI

Aug 11

GeoPhysAdapter: Scale-Matched Geophysical Adaptation for Cross-Domain Landslide Mapping with Vision Foundation Models

arXiv:2608. 09325v1 Announce Type: new Abstract: Newly triggered landslides rarely carry immediate annotations, so cross-domain transferability determines the value of landslide mapping for emergency response and regional risk assessment.

By Zhihang Liu, Mei-Po Kwan, Jinlin Wu, Hao Li

computer-vision

Related stories

MixFrag: Fragility-Guided Mixed-Precision Post-Training Quantization for Vision Transformers

RegimeVGGT: Layer-Wise Spatially Preserving Redundancy Removal for Visual Geometry Grounded Transformer

Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers

X$^2$Localizer: Cross-grained Alignment for Progressive Cross-view Video Geo-localization

Cross-View Sequential Visual Localization with Spatio-Temporal Context Modeling for Autonomous Driving

GeoPhysAdapter: Scale-Matched Geophysical Adaptation for Cross-Domain Landslide Mapping with Vision Foundation Models