SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.02884 · 2024

PosterLLaVa: Constructing a Unified Multi-modal Layout Generator with LLM

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 6 functions out of this paper's own repositories and ran 5 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
posterllava/posterllava canonical 5 of 6
FunctionStatusWhere it lives
expand2square Ran posterllava/posterllava/llava/mm_utils.py
pointer only (licence: NONE) · get_code("592b3c1a88f93d7c")
get_chunk Ran posterllava/posterllava/llava/eval/model_vqa.py
pointer only (licence: NONE) · get_code("42a46570620cd9fa")
is_none Ran posterllava/posterllava/llava/eval/model_vqa_mmbench.py
pointer only (licence: NONE) · get_code("bae18947b56f2be1")
load_image_from_base64 Ran posterllava/posterllava/llava/mm_utils.py
pointer only (licence: NONE) · get_code("c3ee9d07c900dd55")
split_list Ran posterllava/posterllava/llava/eval/model_vqa.py
pointer only (licence: NONE) · get_code("076c252c52cbb161")
process_images Not yet run posterllava/posterllava/llava/mm_utils.py
pointer only (licence: NONE) · get_code("344dff4791fd1381")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Layout generation is the keystone in achieving automated graphic design, requiring arranging the position and size of various multi-modal design elements in a visually pleasing and constraint-following manner. Previous approaches are either inefficient for large-scale applications or lack flexibility for varying design requirements. Our research introduces a unified framework for automated graphic layout generation, leveraging the multi-modal large language model (MLLM) to accommodate diverse design tasks. In contrast, our data-driven method employs structured text (JSON format) and visual instruction tuning to generate layouts under specific visual and textual constraints, including user-defined natural language specifications. We conducted extensive experiments and achieved state-of-the-art (SOTA) performance on public multi-modal layout generation benchmarks, demonstrating the effectiveness of our method. Moreover, recognizing existing datasets' limitations in capturing the complexity of real-world graphic designs, we propose two new datasets for much more challenging tasks (user-constrained generation and complicated poster), further validating our model's utility in real-life settings. Marking by its superior accessibility and adaptability, this approach further automates large-scale graphic design tasks. Finally, we develop an automated text-to-poster system that generates editable SVG posters based on users' design intentions, bridging the gap between layout generation and real-world graphic design applications. This system integrates our proposed layout generation method as the core component, demonstrating its effectiveness in practical scenarios. The code and datasets are open-sourced on https://github.com/posterllava/PosterLLaVA.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2406.02884")
get_code_for_paper("2406.02884")
have("2406.02884")

Connect an agent — have() is free.