Research

Paper

AI LLM March 03, 2026

EduVQA: Benchmarking AI-Generated Video Quality Assessment for Education

Authors

Baoliang Chen, Xinlong Bu, Lingyu Zhu, Hanwei Zhu, Xiangjie Sui

Abstract

While AI-generated content (AIGC) models have achieved remarkable success in generating photorealistic videos, their potential to support visual, story-driven learning in education remains largely untapped. To close this gap, we present EduAIGV-1k, the first benchmark dataset and evaluation framework dedicated to assessing the quality of AI-generated videos (AIGVs) designed to teach foundational math concepts, such as numbers and geometry, to young learners. EduAIGV-1k contains 1,130 short videos produced by ten state-of-the-art text-to-video (T2V) models using 113 pedagogy-oriented prompts. Each video is accompanied by rich, fine-grained annotations along two complementary axes: (1) Perceptual quality, disentangled into spatial and temporal fidelity, and (2) Prompt alignment, labeled at the word-level and sentence-level to quantify the degree to which each mathematical concept in the prompt is accurately grounded in the generated video. These fine-grained annotations transform each video into a multi-dimensional, interpretable supervision signal, far beyond a single quality score. Leveraging this dense feedback, we introduce EduVQA for both perceptual and alignment quality assessment of AIGVs. In particular, we propose a Structured 2D Mixture-of-Experts (S2D-MoE) module, which enhances the dependency between overall quality and each sub-dimension by shared experts and dynamic 2D gating matrix. Extensive experiments show our EduVQA consistently outperforms existing VQA baselines. Both our dataset and code will be publicly available.

Metadata

arXiv ID: 2603.03066
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-03-03
Fetched: 2026-03-04 03:41

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.03066v1</id>\n    <title>EduVQA: Benchmarking AI-Generated Video Quality Assessment for Education</title>\n    <updated>2026-03-03T15:05:27Z</updated>\n    <link href='https://arxiv.org/abs/2603.03066v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.03066v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>While AI-generated content (AIGC) models have achieved remarkable success in generating photorealistic videos, their potential to support visual, story-driven learning in education remains largely untapped. To close this gap, we present EduAIGV-1k, the first benchmark dataset and evaluation framework dedicated to assessing the quality of AI-generated videos (AIGVs) designed to teach foundational math concepts, such as numbers and geometry, to young learners. EduAIGV-1k contains 1,130 short videos produced by ten state-of-the-art text-to-video (T2V) models using 113 pedagogy-oriented prompts. Each video is accompanied by rich, fine-grained annotations along two complementary axes: (1) Perceptual quality, disentangled into spatial and temporal fidelity, and (2) Prompt alignment, labeled at the word-level and sentence-level to quantify the degree to which each mathematical concept in the prompt is accurately grounded in the generated video. These fine-grained annotations transform each video into a multi-dimensional, interpretable supervision signal, far beyond a single quality score. Leveraging this dense feedback, we introduce EduVQA for both perceptual and alignment quality assessment of AIGVs. In particular, we propose a Structured 2D Mixture-of-Experts (S2D-MoE) module, which enhances the dependency between overall quality and each sub-dimension by shared experts and dynamic 2D gating matrix. Extensive experiments show our EduVQA consistently outperforms existing VQA baselines. Both our dataset and code will be publicly available.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <published>2026-03-03T15:05:27Z</published>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Baoliang Chen</name>\n    </author>\n    <author>\n      <name>Xinlong Bu</name>\n    </author>\n    <author>\n      <name>Lingyu Zhu</name>\n    </author>\n    <author>\n      <name>Hanwei Zhu</name>\n    </author>\n    <author>\n      <name>Xiangjie Sui</name>\n    </author>\n  </entry>"
}