Papers
arxiv:2611.02928

Lab2Sim: Turning Real-World Experiment Videos into Interactive Virtual Experiments

Published on Nov 2
· Submitted by
Gary Chen
on Nov 3
Authors:
,
,
,

Abstract

Lab2Sim introduces a benchmark for converting science videos into interactive virtual experiments, and EduVideo2Code improves apparatus fidelity by encoding procedures as state machines for verified code generation.

Science experiment videos demonstrate how experiments are performed, but offer no direct interaction for learners. Turning them into virtual experiments requires not only reproducing the observed apparatus and state changes, but also enforcing the preconditions governing each operation. We introduce Lab2Sim, a benchmark of 218 science experiment videos with evidence-grounded specifications and 11,881 rubric items. To address this task, we propose EduVideo2Code, which extracts experimental procedures hierarchically, encodes them as explicit state machines to guide code generation, and refines the resulting pages through execution-based verification. Experiments show that existing multimodal models readily generate runnable pages but struggle to faithfully reconstruct experimental apparatus. EduVideo2Code consistently improves all four evaluation dimensions across two backbone models, with apparatus fidelity gains of 24.15 points.

Community

Science experiment videos demonstrate how experiments are performed, but offer no direct interaction for learners. Turning them into virtual experiments requires not only reproducing the observed apparatus and state changes, but also enforcing the preconditions governing each operation. We introduce Lab2Sim, a benchmark of 218 science experiment videos with evidence-grounded specifications and 11,881 rubric items. To address this task, we propose EduVideo2Code, which extracts experimental procedures hierarchically, encodes them as explicit state machines to guide code generation, and refines the resulting pages through execution-based verification. Experiments show that existing multimodal models readily generate runnable pages but struggle to faithfully reconstruct experimental apparatus. EduVideo2Code consistently improves all four evaluation dimensions across two backbone models, with apparatus fidelity gains of 24.15 points.

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2611.02928
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.02928 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2611.02928 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.02928 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.