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

arXiv: https://arxiv.org/abs/2605.09378 · HTML: https://mlsanity.com/paper/2605.09378/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 29 references that are in the map.
- First posted on arXiv 10 May 2026.

## Builds on (most cited first, 17 of 17)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [RobustBench: a standardized adversarial robustness benchmark](https://mlsanity.com/paper/2010.09670/) (2020)
- [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024)
- [VideoPoet: A Large Language Model for Zero-Shot Video Generation](https://mlsanity.com/paper/2312.14125/) (2023)
- [Generative Multimodal Models are In-Context Learners](https://mlsanity.com/paper/2312.13286/) (2023)
- [EvalCrafter: Benchmarking and Evaluating Large Video Generation Models](https://mlsanity.com/paper/2310.11440/) (2023)
- [StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text](https://mlsanity.com/paper/2403.14773/) (2024)
- [VideoPhy: Evaluating Physical Commonsense for Video Generation](https://mlsanity.com/paper/2406.03520/) (2024)
- [Towards Open-ended Visual Quality Comparison](https://mlsanity.com/paper/2402.16641/) (2024)
- [Subjective-Aligned Dataset and Metric for Text-to-Video Quality Assessment](https://mlsanity.com/paper/2403.11956/) (2024)
- [Seeing Sound, Hearing Sight: Uncovering Modality Bias and Conflict of AI models in Sound Localization](https://mlsanity.com/paper/2505.11217/) (2025)
- [Uni-Retrieval: A Multi-Style Retrieval Framework for STEM's Education](https://mlsanity.com/paper/2502.05863/) (2025)
- [Storyboard guided Alignment for Fine-grained Video Action Recognition](https://mlsanity.com/paper/2410.14238/) (2024)

## Built on by (most cited first, 1 of 1)

- [MMOE: Modernizing Diffusion Transformers with Efficient Expert Design](https://mlsanity.com/paper/2607.24665/) (2026)

## Abstract (arXiv)

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.