Smaller But Better: Unifying Layout Generation with Smaller Large Language Models
International Journal of Computer Vision · 2025-07 · 133 (7) · 3891-3917
DOI: 10.1007/s11263-025-02353-2 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Computer Vision, online erschienen am 12.02.2025. Verfasst von Peirong Zhang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 80 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
We propose LGGPT, an LLM-based model tailored for unified layout generation. First, we propose Arbitrary Layout Instruction (ALI) and Universal Layout Response (ULR) as the uniform I/O template. ALI accommodates arbitrary layout generation task inputs across multiple layout domains, enabling LGGPT to unify both task-generic and domain-generic layout generation hitherto unexplored. Collectively, ALI and ULR boast a succinct structure that forgoes superfluous tokens typically found in existing HTML-based formats, facilitating efficient instruction tuning and boosting unified generation performance. In addition, we propose an Interval Quantization Encoding (IQE) strategy that compresses ALI into a more condensed structure. IQE precisely preserves valid layout clues while eliminating the less informative placeholders, facilitating LGGPT to capture complex and variable layout generation conditions during the unified training process. Experimental results demonstrate that LGGPT achieves superior or on par performance compared to existing methods. Notably, LGGPT strikes a prominent balance between proficiency and efficiency with a compact 1.5B parameter LLM, which beats prior 7B or 175B models even in the most extensive and challenging unified scenario. Furthermore, we underscore the necessity of employing LLMs for unified layout generation and suggest that 1.5B could be an optimal parameter size by comparing LLMs of varying scales. Code is available at https://github.com/NiceRingNode/LGGPT.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Zhang, P., Zhang, J., Cao, J., Li, H., & Jin, L. (2025). Smaller But Better: Unifying Layout Generation with Smaller Large Language Models. International Journal of Computer Vision, 133(7), 3891-3917. https://doi.org/10.1007/s11263-025-02353-2
Vancouver
Zhang P, Zhang J, Cao J, Li H, Jin L. Smaller But Better: Unifying Layout Generation with Smaller Large Language Models. International Journal of Computer Vision. 2025;133(7):3891-3917. doi:10.1007/s11263-025-02353-2
BibTeX
@article{Zhang2025,
author = {Zhang, Peirong and Zhang, Jiaxin and Cao, Jiahuan and Li, Hongliang and Jin, Lianwen},
title = {Smaller But Better: Unifying Layout Generation with Smaller Large Language Models},
journal = {International Journal of Computer Vision},
year = {2025},
volume = {133},
number = {7},
pages = {3891--3917},
doi = {10.1007/s11263-025-02353-2}
}
EUVIMED