EduStory: A Unified Framework for Pedagogically-Consistent Multi-Shot STEM Instructional Video Generation

TL;DR

EduStory is a comprehensive framework designed to generate pedagogically coherent multi-shot STEM instructional videos, emphasizing knowledge consistency, structured control, and specialized evaluation metrics.

Contribution

It introduces a unified approach combining pedagogical state modeling, script-guided control, and a new benchmark for evaluating long-horizon instructional video generation in STEM.

Findings

Domain-aware state modeling reduces narrative breakdown.

Structured control improves alignment with instructional intent.

The EduVideoBench benchmark enables rigorous evaluation of pedagogical coherence.

Abstract

Long-horizon video generation has advanced in visual quality, yet existing methods still struggle to maintain knowledge consistency and coherent pedagogical narratives across multi-shot instructional videos, especially in STEM domains. To address these challenges, we propose EduStory, a unified framework for reliable instructional video generation. EduStory integrates pedagogical state modeling to track persistent knowledge states, script-guided structured control to organize multi-shot narratives, and learning-oriented evaluation metrics to assess knowledge fidelity and constraint satisfaction. To support rigorous evaluation, we further introduce EduVideoBench, a diagnostic benchmark with multi-granularity annotations, including pedagogical storyboards, shot-level semantics, and knowledge state transitions, together with baseline tasks for controllable instructional video generation. Extensive experiments demonstrate that domain-aware state modeling and structured control substantially reduce narrative breakdown and improve alignment with instructional intent. These results highlight the significance of domain-specific structural constraints and tailored benchmarks for advancing reliable, controllable, and also trustworthy long-horizon video generation.