arXiv AI August 18, 2026 By Mohamed Amine Kerkouri, Marouane Tliba, Aladine Chetouani, Ulas Bagci, Alessandro Bruno

Matched Outcomes, Divergent Gaze: How Foveated MLLMs Search Compared to Humans

arXiv:2608. 16514v1 Announce Type: cross Abstract: Human visual search is serial: the fovea must land on a candidate to confirm it, and those landings form a scanpath.

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

arXiv Machine Learning

Jun 15

Gaze Heads: How VLMs Look at What They Describe

arXiv:2606. 14703v1 Announce Type: cross Abstract: How a vision-language model internally solves the task of describing an image is far from obvious.

By Rohit Gandikota, David Bau

llms multimodal

arXiv AI

Jul 14

Debiasing Central Fixation Confounds Reveals a Peripheral "Sweet Spot" for Human-like Scanpaths in Hard-Attention Vision

arXiv:2602. 14834v2 Announce Type: replace-cross Abstract: Human eye movements in visual recognition reflect a balance between foveal sampling and peripheral context.

By Pengcheng Pan, Yonekura Shogo, Yasuo Kuniyosh

benchmarks safety

arXiv AI

Jun 17

Visuals Lie, Consistency Speaks: Disentangling Spatial Attention from Reliability in Vision-Language Models

arXiv:2606. 17389v1 Announce Type: cross Abstract: Multimodal Foundation Models are increasingly used as reasoning agents, making reliability, knowing when a model may hallucinate, critical.

By Logan Mann, Yi Xia, Ajit Saravanan, Ishan Dave, Saadullah Ismail, Shikhar Shiromani, Emily Huang, Ruizhe Li, Kevin Zhu

llms agents multimodal

arXiv AI

Jul 20

An Exam for Active Observers

arXiv:2607. 16165v1 Announce Type: cross Abstract: Human vision is a closed loop: gaze is continuously redirected by intermediate hypotheses rather than a single snapshot.

By Jiarui Zhang, Muzi Tao, Shangshang Wang, Ollie Liu, Xuezhe Ma, Willie Neiswanger

llms multimodal benchmarks

arXiv AI

Jun 16

Attention, not scale, drives human-AI alignment in multimodal language prediction

arXiv:2308. 06035v4 Announce Type: replace Abstract: Humans routinely draw on visual context to predict upcoming words.

By Viktor Kewenig, Andrew Lampinen, Samuel A. Nastase, Christopher Edwards, Quitterie Lacome D'Elascombe, Akilles Rechardt, Jeremy I Skipper, Gabriella Vigliocco

llms multimodal benchmarks safety

arXiv AI

Jul 20

Ask Twice, Look Twice: Prompt Echoing Resolves the Question-First Paradox in Vision-Language Models

arXiv:2607. 15565v1 Announce Type: cross Abstract: Where should the question go in a vision-language model (VLM) prompt: before the image or after it?

By Rakshanda Hassan Abhinandan, John Galeotti, Deva Ramanan, Gautam Rajendrakumar Gare

llms nlp fine-tuning multimodal benchmarks

Related stories

Gaze Heads: How VLMs Look at What They Describe

Debiasing Central Fixation Confounds Reveals a Peripheral "Sweet Spot" for Human-like Scanpaths in Hard-Attention Vision

Visuals Lie, Consistency Speaks: Disentangling Spatial Attention from Reliability in Vision-Language Models

An Exam for Active Observers

Attention, not scale, drives human-AI alignment in multimodal language prediction

Ask Twice, Look Twice: Prompt Echoing Resolves the Question-First Paradox in Vision-Language Models