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

• URL: http://arxiv.org/abs/2605.09378v1
• Date: Sun, 10 May 2026 07:03:37 GMT
• Title: EduStory: A Unified Framework for Pedagogically-Consistent Multi-Shot STEM Instructional Video Generation
• Abstract summary: EduStory is a unified framework for reliable instructional video generation.<n>It integrates pedagogical state modeling to track persistent knowledge states, script-guided structured control to organize multi-shot narratives, and learning-oriented evaluation metrics.<n>EduVideoBench is a diagnostic benchmark with multi-granularity annotations, including pedagogical storyboards, shot-level semantics, and knowledge state transitions.
• Score: 40.60762124779023
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• STORM: Internalized Modeling for Spatial-Temporal Reasoning in Video-Language Models [81.32710031596591]
  Video reasoning tasks require tracking motion, temporal order, and evolving visual states across frames.<n>Existing methods built on vision-language models (LVLMs) often address this challenge by externalizing reasoning through chain-of-thought (CoT)<n>We propose STORMS, a two-stage framework that teaches LVLMs to reason through bounded continuous latent trajectories instead of explicit textual CoT.
  arXiv  Detail & Related papers  (2026-05-25T16:33:00Z)
• Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance [55.32799307123252]
  We introduce a scalable data generation pipeline that transforms existing video editing pairs into high-fidelity training quadruplets.<n>We propose a unified editing architecture, Kiwi-Edit, that synergizes learnable queries and latent visual features for reference semantic guidance.
  arXiv  Detail & Related papers  (2026-03-02T18:46:28Z)
• Beyond End-to-End Video Models: An LLM-Based Multi-Agent System for Educational Video Generation [15.004606775581356]
  LAVES is a hierarchical multi-agent system for generating high-quality instructional videos from educational problems.<n>In large-scale deployments, LAVES achieves a throughput exceeding one million videos per day, delivering over a 95% reduction in cost.
  arXiv  Detail & Related papers  (2026-02-12T10:14:36Z)
• UniUGP: Unifying Understanding, Generation, and Planing For End-to-end Autonomous Driving [35.86460001147528]
  We construct specialized datasets providing reasoning and planning annotations for complex scenarios.<n>A unified Understanding-Generation-Planning framework, named UniUGP, is proposed to synergize scene reasoning, future video generation, and trajectory planning.<n>Experiments demonstrate state-of-the-art performance in perception, reasoning, and decision-making, with superior generalization to challenging long-tail situations.
  arXiv  Detail & Related papers  (2025-12-10T17:50:29Z)
• SlideBot: A Multi-Agent Framework for Generating Informative, Reliable, Multi-Modal Presentations [29.874786844781138]
  Large Language Models (LLMs) have shown immense potential in education, automating tasks like quiz generation and content summarization.<n>Existing LLM-based solutions often fail to produce reliable and informative outputs, limiting their educational value.<n>We introduce SlideBot - a modular, multi-agent slide generation framework that integrates LLMs with retrieval, structured planning, and code generation.
  arXiv  Detail & Related papers  (2025-11-12T23:12:05Z)
• ID-Composer: Multi-Subject Video Synthesis with Hierarchical Identity Preservation [48.59900036213667]
  Video generative models pretrained on large-scale datasets can produce high-quality videos, but are often conditioned on text or a single image.<n>We introduce ID-Composer, a novel framework that tackles multi-subject video generation from a text prompt and reference images.
  arXiv  Detail & Related papers  (2025-11-01T11:29:14Z)
• Dual Learning with Dynamic Knowledge Distillation and Soft Alignment for Partially Relevant Video Retrieval [53.54695034420311]
  In practice, videos are typically untrimmed in long durations with much more complicated background content.<n>We propose a novel framework that distills generalization knowledge from a powerful large-scale vision-language pre-trained model.<n>Experiment results demonstrate that our proposed model achieves state-of-the-art performance on TVR, ActivityNet, and Charades-STA datasets.
  arXiv  Detail & Related papers  (2025-10-14T08:38:20Z)
• Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models [78.32948112203228]
  Video understanding represents the most challenging frontier in computer vision.<n>Recent emergence of Video-Large Multitemporal Models has demonstrated remarkable capabilities in video understanding tasks.<n>Survey aims to provide researchers and practitioners with a unified framework for advancing Video-LMM capabilities.
  arXiv  Detail & Related papers  (2025-10-06T17:10:44Z)
• VidCLearn: A Continual Learning Approach for Text-to-Video Generation [11.861060763379236]
  VidCLearn is a continual learning framework for text-to-video generation.<n>We introduce a novel temporal consistency loss to enhance motion smoothness and a video retrieval module to provide structural guidance at inference.<n>Our architecture is also designed to be more computationally efficient than existing models while retaining satisfactory generation performance.
  arXiv  Detail & Related papers  (2025-09-21T07:34:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.