Code2Video: A Code-centric Paradigm for Educational Video Generation

Papers with Code Trending Papers
code-centric educational-video-generation generative-models vision-language-models multi-agent benchmark python

Summary

Code2Video is a code-centric agent framework for generating educational videos, improving coherence and interpretability over direct code generation. It includes a multi-agent system and a new benchmark for evaluation.

While recent generative models advance pixel-space video synthesis, they remain limited in producing professional educational videos, which demand disciplinary knowledge, precise visual structures, and coherent transitions, limiting their applicability in educational scenarios. Intuitively, such requirements are better addressed through the manipulation of a renderable environment, which can be explicitly controlled via logical commands (e.g., code). In this work, we propose Code2Video, a code-centric agent framework for generating educational videos via executable Python code. The framework comprises three collaborative agents: (i) Planner, which structures lecture content into temporally coherent flows and prepares corresponding visual assets; (ii) Coder, which converts structured instructions into executable Python codes while incorporating scope-guided auto-fix to enhance efficiency; and (iii) Critic, which leverages vision-language models (VLM) with visual anchor prompts to refine spatial layout and ensure clarity. To support systematic evaluation, we build MMMC, a benchmark of professionally produced, discipline-specific educational videos. We evaluate MMMC across diverse dimensions, including VLM-as-a-Judge aesthetic scores, code efficiency, and particularly, TeachQuiz, a novel end-to-end metric that quantifies how well a VLM, after unlearning, can recover knowledge by watching the generated videos. Our results demonstrate the potential of Code2Video as a scalable, interpretable, and controllable approach, achieving 40% improvement over direct code generation and producing videos comparable to human-crafted tutorials. The code and datasets are available at https://github.com/showlab/Code2Video.
Original Article
View Cached Full Text

Cached at: 08/17/26, 03:38 AM

Paper page - Code2Video: A Code-centric Paradigm for Educational Video Generation

Source: https://huggingface.co/papers/2510.01174 Published on Oct 1, 2025

·

Submitted byhttps://huggingface.co/taesiri

taesirion Oct 2, 2025

Abstract

Code2Video generates educational videos using a code-centric agent framework, improving coherence and interpretability compared to direct code generation.

While recentgenerative modelsadvancepixel-space video synthesis, they remain limited in producing professional educational videos, which demand disciplinary knowledge, precise visual structures, and coherent transitions, limiting their applicability in educational scenarios. Intuitively, such requirements are better addressed through the manipulation of a renderable environment, which can be explicitly controlled vialogical commands(e.g., code). In this work, we propose Code2Video, acode-centric agent frameworkfor generating educational videos via executable Python code. The framework comprises three collaborative agents: (i)Planner, which structures lecture content into temporally coherent flows and prepares corresponding visual assets; (ii)Coder, which converts structured instructions into executable Python codes while incorporating scope-guided auto-fix to enhance efficiency; and (iii)Critic, which leveragesvision-language models(VLM) with visual anchor prompts to refine spatial layout and ensure clarity. To support systematic evaluation, we buildMMMC, a benchmark of professionally produced, discipline-specific educational videos. We evaluateMMMCacross diverse dimensions, includingVLM-as-a-Judge aesthetic scores, code efficiency, and particularly,TeachQuiz, a novel end-to-end metric that quantifies how well aVLM, after unlearning, can recover knowledge by watching the generated videos. Our results demonstrate the potential of Code2Video as a scalable, interpretable, and controllable approach, achieving 40% improvement over direct code generation and producing videos comparable tohuman-crafted tutorials. The code and datasets are available at https://github.com/showlab/Code2Video.

View arXiv pageView PDFProject pageGitHub1.97kAdd to collection

Get this paper in your agent:

hf papers read 2510\.01174

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2510.01174 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2510.01174 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2510.01174 in a Space README.md to link it from this page.

Collections including this paper7

Browse 7 collections that include this paper

Similar Articles

Coding Agent Is Good As World Simulator

arXiv cs.AI

This paper presents an agentic framework that uses coding agents to generate physically plausible world simulations from natural language prompts, outperforming video-based models in physical accuracy and instruction fidelity.

CogOmniControl: Reasoning-Driven Controllable Video Generation via Creative Intent Cognition

Hugging Face Daily Papers

CogOmniControl is a reasoning-driven framework for controllable video generation that uses a specialized vision-language model (CogVLM) trained on anime production data to infer creative intent from sparse conditions, then guides a diffusion-based generator via reinforcement learning, achieving state-of-the-art results on new benchmarks.