Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Visual Agnosia01:12

Visual Agnosia

981
Visual agnosia is a condition characterized by the inability to recognize visually presented objects despite having normal vision. For instance, a person with visual agnosia can describe the shape and color of an object but cannot identify or name it. This impairment does not affect their visual field, acuity, color vision, brightness discrimination, language, or memory. An example of this condition in a social setting is someone at a dinner party asking for "that silver thing with a round...
981
Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

395
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...
395

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Further evidence for embodied cognition: The link between spontaneous respiratory oscillations and number processing.

PloS one·2026
Same author

Comment on "Integrating large language models and active inference to understand eye movements in reading and dyslexia" by Donnarumma et al.

Physics of life reviews·2026
Same author

Biomarkers of stroke recovery using EEG-based resting-state functional connectivity: a systematic review.

Journal of neuroengineering and rehabilitation·2026
Same author

Obesity accelerates brain ageing: a multimodal imaging study.

Brain communications·2025
Same author

Unveiling the sensorimotor basis of numerical processing: A functional near-infrared spectroscopy (fNIRS) study.

NeuroImage·2025
Same author

Temporal momentum: an online replication and beyond.

Psychological research·2025
Same journal

Analysis of strength degradation of coal and rock masses and stability of mined areas under long term immersion environment.

PloS one·2026
Same journal

Biogenic Silver-Selenium nanocomposite with anticancer activity and potent efficacy against vancomycin-resistant Staphylococcus aureus.

PloS one·2026
Same journal

Preparation and physicochemical characterization of a biodegradable chitosan/carboxymethyl cellulose hydrogel synthesized in NaOH/urea medium.

PloS one·2026
Same journal

Action-guilt, survivor-guilt, and depression in combat-related PTSD.

PloS one·2026
Same journal

Explainable machine learning for predicting activities of daily living at discharge in stroke patients: A retrospective study using SHAP interpretability.

PloS one·2026
Same journal

Deep learning based two-way feature depiction model for brain tumor detection.

PloS one·2026
See all related articles

Related Experiment Video

Updated: Jan 18, 2026

Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

2.3K

Visual enumeration remains challenging for multimodal generative AI.

Alberto Testolin1, Kuinan Hou2, Marco Zorzi3,4

  • 1Department of General Psychology and Department of Mathematics, University of Padova, Padova, Italy.

Plos One
|September 12, 2025
PubMed
Summary
This summary is machine-generated.

Current AI models struggle with visual enumeration, failing to accurately count objects in images or generate images with specific numbers of items. This suggests that simply increasing AI model size does not develop robust counting skills.

More Related Videos

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.0K

Related Experiment Videos

Last Updated: Jan 18, 2026

Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

2.3K
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.0K

Area of Science:

  • Artificial Intelligence
  • Cognitive Science
  • Computer Vision

Background:

  • Humans and animals possess innate numerical abilities, while current AI systems exhibit limited visual enumeration skills.
  • Evaluating AI's number sense is crucial for advancing multimodal foundation models.

Purpose of the Study:

  • To introduce two cognitive science-inspired benchmark tasks for precisely evaluating visual enumeration capabilities in AI models.
  • To provide an objective measure of AI's number sense and counting proficiency.

Main Methods:

  • Assessed popular visual question answering (VQA), image-to-text, and text-to-image AI models.
  • Utilized benchmark tasks to evaluate AI's ability to name object counts and generate images with specific numerosity.

Main Results:

  • Advanced AI models demonstrated low accuracy in both naming object counts and generating images with target numbers.
  • Model performance degraded significantly for numbers beyond the subitizing range, with errors often dependent on object category.
  • AI models exhibited notable errors even with small numbers, unlike human behavior.

Conclusions:

  • Developing intuitive visual number understanding remains a significant challenge for AI.
  • Increasing AI model size alone is unlikely to foster systematic counting skills.
  • The study releases benchmark code to aid future AI enumeration skill evaluations.