Video models are zero-shot learners and reasoners

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wiedemer, Thaddäus, Li, Yuxuan, Vicol, Paul, Gu, Shixiang Shane, Matarese, Nick, Swersky, Kevin, Kim, Been, Jaini, Priyank, Geirhos, Robert
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915522912714752
author Wiedemer, Thaddäus
Li, Yuxuan
Vicol, Paul
Gu, Shixiang Shane
Matarese, Nick
Swersky, Kevin
Kim, Been
Jaini, Priyank
Geirhos, Robert
author_facet Wiedemer, Thaddäus
Li, Yuxuan
Vicol, Paul
Gu, Shixiang Shane
Matarese, Nick
Swersky, Kevin
Kim, Been
Jaini, Priyank
Geirhos, Robert
contents The remarkable zero-shot capabilities of Large Language Models (LLMs) have propelled natural language processing from task-specific models to unified, generalist foundation models. This transformation emerged from simple primitives: large, generative models trained on web-scale data. Curiously, the same primitives apply to today's generative video models. Could video models be on a trajectory towards general-purpose vision understanding, much like LLMs developed general-purpose language understanding? We demonstrate that Veo 3 can solve a broad variety of tasks it wasn't explicitly trained for: segmenting objects, detecting edges, editing images, understanding physical properties, recognizing object affordances, simulating tool use, and more. These abilities to perceive, model, and manipulate the visual world enable early forms of visual reasoning like maze and symmetry solving. Veo's emergent zero-shot capabilities indicate that video models are on a path to becoming unified, generalist vision foundation models.
format Preprint
id arxiv_https___arxiv_org_abs_2509_20328
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Video models are zero-shot learners and reasoners
Wiedemer, Thaddäus
Li, Yuxuan
Vicol, Paul
Gu, Shixiang Shane
Matarese, Nick
Swersky, Kevin
Kim, Been
Jaini, Priyank
Geirhos, Robert
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Robotics
The remarkable zero-shot capabilities of Large Language Models (LLMs) have propelled natural language processing from task-specific models to unified, generalist foundation models. This transformation emerged from simple primitives: large, generative models trained on web-scale data. Curiously, the same primitives apply to today's generative video models. Could video models be on a trajectory towards general-purpose vision understanding, much like LLMs developed general-purpose language understanding? We demonstrate that Veo 3 can solve a broad variety of tasks it wasn't explicitly trained for: segmenting objects, detecting edges, editing images, understanding physical properties, recognizing object affordances, simulating tool use, and more. These abilities to perceive, model, and manipulate the visual world enable early forms of visual reasoning like maze and symmetry solving. Veo's emergent zero-shot capabilities indicate that video models are on a path to becoming unified, generalist vision foundation models.
title Video models are zero-shot learners and reasoners
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2509.20328