Research map / Video / Video generation
Code2Video: A Code-centric Paradigm for Educational Video Creation
Yanzhe Chen, Kevin Qinghong Lin, Mike Zheng Shou
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add the Planner (ablation) | Code2Video (GPT-4.1) · MMMC | TeachQuiz: 82.0 -> 40.5 | Improved |
| add the Planner (ablation) | Code2Video (GPT-4.1) · MMMC | aesthetics average: 79.0 -> 38.1 | Improved |
| add the External Database (ablation) | Code2Video (GPT-4.1) · MMMC | TeachQuiz: 82.0 -> 52.0 | Improved |
| add the External Database (ablation) | Code2Video (GPT-4.1) · MMMC | aesthetics average: 79.0 -> 68.1 | Improved |
| add Visual Anchor prompt (ablation) | Code2Video (GPT-4.1) · MMMC | TeachQuiz: 82.0 -> 55.2 | Improved |
| add the Critic (ablation) | Code2Video (GPT-4.1) · MMMC | TeachQuiz: 82.0 -> 60.7 | Improved |
| add parallel execution (ablation) | Code2Video (GPT-4.1) · MMMC | time per topic (min): 86.6 -> 15.4 | Improved |
| add ScopeRefine instead of Retry (ablation) | Code2Video (GPT-4.1) · MMMC | time per topic (min): 42.9 -> 15.4 | Improved |
| add ScopeRefine instead of full-code debug (ablation) | Code2Video (GPT-4.1) · MMMC | time per topic (min): 39.2 -> 15.4 | Improved |
| use 6x6 anchor grid instead of 8x8 (ablation) | Code2Video (GPT-4.1) · MMMC | aesthetics average: 76.0 -> 79.0 | Improved |
| use 6x6 anchor grid instead of 4x4 (ablation) | Code2Video (GPT-4.1) · MMMC | aesthetics average: 76.9 -> 79.0 | Improved |
| use 6x6 anchors instead of self-directed placement (ablation) | Code2Video (GPT-4.1) · MMMC | aesthetics average: 70.3 -> 79.0 | Improved |
Closest papers by meaning
- PRISM: A Benchmark for Programmatic Spatial-Temporal Reasoning (NeurIPS 2026 · similarity 0.87)
- Animation2Code: Evaluating Temporal Visual Reasoning in Video-to-Code Generation (NeurIPS 2026 · similarity 0.86)
- GRADEO: Towards Human-Like Evaluation for Text-to-Video Generation via Multi-Step Reasoning (ICML 2025 · similarity 0.85)
- JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence (ICLR 2026 · similarity 0.85)
- ShowHowTo: Generating Scene-Conditioned Step-by-Step Visual Instructions (CVPR 2025 · similarity 0.84)
- Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision (ICLR 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
