AI Paper Atlas

Research map / Video / Video generation

Code2Video: A Code-centric Paradigm for Educational Video Creation

Yanzhe Chen, Kevin Qinghong Lin, Mike Zheng Shou

ICML 2026 · Video › Video generation · approach: Diffusion-based human image animation

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 changedWhereMeasuredEffect
add the Planner (ablation)Code2Video (GPT-4.1) · MMMCTeachQuiz: 82.0 -> 40.5Improved
add the Planner (ablation)Code2Video (GPT-4.1) · MMMCaesthetics average: 79.0 -> 38.1Improved
add the External Database (ablation)Code2Video (GPT-4.1) · MMMCTeachQuiz: 82.0 -> 52.0Improved
add the External Database (ablation)Code2Video (GPT-4.1) · MMMCaesthetics average: 79.0 -> 68.1Improved
add Visual Anchor prompt (ablation)Code2Video (GPT-4.1) · MMMCTeachQuiz: 82.0 -> 55.2Improved
add the Critic (ablation)Code2Video (GPT-4.1) · MMMCTeachQuiz: 82.0 -> 60.7Improved
add parallel execution (ablation)Code2Video (GPT-4.1) · MMMCtime per topic (min): 86.6 -> 15.4Improved
add ScopeRefine instead of Retry (ablation)Code2Video (GPT-4.1) · MMMCtime per topic (min): 42.9 -> 15.4Improved
add ScopeRefine instead of full-code debug (ablation)Code2Video (GPT-4.1) · MMMCtime per topic (min): 39.2 -> 15.4Improved
use 6x6 anchor grid instead of 8x8 (ablation)Code2Video (GPT-4.1) · MMMCaesthetics average: 76.0 -> 79.0Improved
use 6x6 anchor grid instead of 4x4 (ablation)Code2Video (GPT-4.1) · MMMCaesthetics average: 76.9 -> 79.0Improved
use 6x6 anchors instead of self-directed placement (ablation)Code2Video (GPT-4.1) · MMMCaesthetics average: 70.3 -> 79.0Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy