Table of Links Abstract and 1 Introduction Abstract and 1 Introduction 2 Related Work 2.1 Program Synthesis 2.1 Program Synthesis 2.2 Creativity Support Tools for Animation 2.2 Creativity Support Tools for Animation 2.3 Generative Tools for Design 2.3 Generative Tools for Design 3 Formative Steps 3 Formative Steps 4 Logomotion System and 4.1 Input 4 Logomotion System and 4.1 Input 4.2 Preprocess Visual Information 4.2 Preprocess Visual Information 4.3 Visually-Grounded Code Synthesis 4.3 Visually-Grounded Code Synthesis 5 Evaluations 5 Evaluations 5.1 Evaluation: Program Repair 5.1 Evaluation: Program Repair 5.2 Methodology 5.2 Methodology 5.3 Findings 5.3 Findings 6 Evaluation with Novices 6 Evaluation with Novices 7 Discussion and 7.1 Breaking Away from Templates 7 Discussion and 7.1 Breaking Away from Templates 7.2 Generating Code Around Visuals 7.2 Generating Code Around Visuals 7.3 Limitations 7.3 Limitations 8 Conclusion and References 8 Conclusion and References 5.1 Evaluation: Program Repair We next conducted an evaluation specifically centered around the visually-grounded program repair stage to methodically understand the sorts of errors LogoMotion would make (RQ3) and was capable of debugging (RQ4). We provide empirical analysis of this stage testing different experimental settings. 5.2 Methodology 68% of the animation runs from the outset (after program synthesis) were error-free and did not require program repair. The other 32% required the program repair stage. Within this stage, we modulated a 1) hyperparameter 𝑘 and 2) whether or not image context was provided. 𝑘 upper bounded the number of attempts an LLM could take to solve the bug, and was varied from 1 to 4 attempts. Varying 𝑘 is modeled after the pass@k methodology proposed by HumanEval [21], where 𝑘 code samples are generated in attempts to solve a problem and the fraction of problems solved is the solve rate. In this case, the pass@k framework is applied in the context of program repair / self-refinement. Authors:
(1) Vivian Liu, Columbia University (vivian@cs.columbia.edu);
(2) Rubaiat Habib Kazi, Adobe Research (rhabib@adobe.com);
(3) Li-Yi Wei, Adobe Research (lwei@adobe.com);
(4) Matthew Fisher, Adobe Research (matfishe@adobe.com);
(5) Timothy Langlois, Adobe Research (tlangloi@adobe.com);
(6) Seth Walker, Adobe Research (swalker@adobe.com);
(7) Lydia Chilton, Columbia University (chilton@cs.columbia.edu). Authors: Authors: (1) Vivian Liu, Columbia University (vivian@cs.columbia.edu); (2) Rubaiat Habib Kazi, Adobe Research (rhabib@adobe.com); (3) Li-Yi Wei, Adobe Research (lwei@adobe.com); (4) Matthew Fisher, Adobe Research (matfishe@adobe.com); (5) Timothy Langlois, Adobe Research (tlangloi@adobe.com); (6) Seth Walker, Adobe Research (swalker@adobe.com); (7) Lydia Chilton, Columbia University (chilton@cs.columbia.edu). This paper is available on arxiv under CC BY-NC-ND 4.0 DEED license. This paper is available on arxiv under CC BY-NC-ND 4.0 DEED license. available on arxiv available on arxiv

Part of HackerNoon's growing list of open-source research papers, promoting free access to academic material.

Adobe

Analyzing LogoMotion Errors in Position, Scale, and Animation Logic

Can an AI Animate Logos Better Than a Human? 

Read My Stories

Too Long; Didn't Read

Make resilience your competitive advantage

Can AI Fix Its Own Bugs? A Look at LogoMotion’s Self-Refinement

About Author

Comments

TOPICS

THIS ARTICLE WAS FEATURED IN

Related Stories

Untitled Story

Can AI Animate Your Logo? LogoMotion Says Hell Yeah!

Turn Static Logos Into Dynamic Animations With AI

Your Next Animator Might Be an Algorithm

LogoMotion and the Art of Semantic Animation

How Designers Approach Logo Animation

Can AI Animate Your Logo? LogoMotion Says Hell Yeah!

Turn Static Logos Into Dynamic Animations With AI

Your Next Animator Might Be an Algorithm

LogoMotion and the Art of Semantic Animation

How Designers Approach Logo Animation

Light-Mode

Classic

Newspaper

Dark-Mode

Neon Noir

Minty

HN StartUps