Saved in:
Bibliographic Details
Main Authors: Khan, Faizan Farooq, Joseph, K J, Goswami, Koustava, Elhoseiny, Mohamed, Srinivasan, Balaji Vasan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.03335
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917121372454912
author Khan, Faizan Farooq
Joseph, K J
Goswami, Koustava
Elhoseiny, Mohamed
Srinivasan, Balaji Vasan
author_facet Khan, Faizan Farooq
Joseph, K J
Goswami, Koustava
Elhoseiny, Mohamed
Srinivasan, Balaji Vasan
contents Design generation, in its essence, is a step-by-step process where designers progressively refine and enhance their work through careful modifications. Despite this fundamental characteristic, existing approaches mainly treat design synthesis as a single-step generation problem, significantly underestimating the inherent complexity of the creative process. To bridge this gap, we propose a novel problem setting called Step-by-Step Layered Design Generation, which tasks a machine learning model with generating a design that adheres to a sequence of instructions from a designer. Leveraging recent advancements in multi-modal LLMs, we propose SLEDGE: Step-by-step LayEred Design GEnerator to model each update to a design as an atomic, layered change over its previous state, while being grounded in the instruction. To complement our new problem setting, we introduce a new evaluation suite, including a dataset and a benchmark. Our exhaustive experimental analysis and comparison with state-of-the-art approaches tailored to our new setup demonstrate the efficacy of our approach. We hope our work will attract attention to this pragmatic and under-explored research area.
format Preprint
id arxiv_https___arxiv_org_abs_2512_03335
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Step-by-step Layered Design Generation
Khan, Faizan Farooq
Joseph, K J
Goswami, Koustava
Elhoseiny, Mohamed
Srinivasan, Balaji Vasan
Computer Vision and Pattern Recognition
Machine Learning
Design generation, in its essence, is a step-by-step process where designers progressively refine and enhance their work through careful modifications. Despite this fundamental characteristic, existing approaches mainly treat design synthesis as a single-step generation problem, significantly underestimating the inherent complexity of the creative process. To bridge this gap, we propose a novel problem setting called Step-by-Step Layered Design Generation, which tasks a machine learning model with generating a design that adheres to a sequence of instructions from a designer. Leveraging recent advancements in multi-modal LLMs, we propose SLEDGE: Step-by-step LayEred Design GEnerator to model each update to a design as an atomic, layered change over its previous state, while being grounded in the instruction. To complement our new problem setting, we introduce a new evaluation suite, including a dataset and a benchmark. Our exhaustive experimental analysis and comparison with state-of-the-art approaches tailored to our new setup demonstrate the efficacy of our approach. We hope our work will attract attention to this pragmatic and under-explored research area.
title Step-by-step Layered Design Generation
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2512.03335