We present iPoster, an interactive layout generation framework that empowers users to guide content-aware poster layout design by specifying flexible constraints. iPoster enables users to specify partial intentions within the intention module, such as element categories, sizes, positions, or coarse initial drafts. Then, the generation module instantly generates refined, context-sensitive layouts that faithfully respect these constraints. iPoster employs a unified graph-enhanced diffusion architecture that supports various design tasks under user-specified constraints. These constraints are enforced through masking strategies that precisely preserve user input at every denoising step. A cross content-aware attention module aligns generated elements with salient regions of the canvas, ensuring visual coherence. Extensive experiments show that iPoster not only achieves state-of-the-art layout quality, but offers a responsive and controllable framework for poster layout design with constraints.
Figures & tables
Figure 1. The overall training framework of content-aware layout generation model (shown in the left). The core module is Cross Content-aware Attention Module (shown in the right).
Figure 2. The construction process of GBLM and GILM . For each bboxi , c is the element category, cx and cy are its center coordinates, and w and h are its width and height. Each image is divided into r rows and c columns of patches. See Section 3.2.2 for details.
Figure 3. iPoster’s interactive framework, showing user interaction and mask execution during inference.
Figure 4
PosterLlama ( Seol et al., 2024 )
PosterO ( Hsu and Peng, 2025 )
LayoutDiT ( Li et al., 2024 )
iPoster
Params
7B
8B
49M
33M
Inference Time(s)
7.6
7.5
1.5
1.1
Table 2. Comparison of model parameter counts and end-to-end inference latency for batch size of 1.
Figure 5. Illustration of a representative user scenario. The left side presents a schematic UI mockup depicting user interactions, and the right side shows the resulting layout candidates along with the final posters automatically rendered from them.
Text prompting is an indirect interface for poster generation, requiring users to encode inherently two-dimensional composition intent into a one-dimensional sequence of words. We introduce a Spatial Canvas Interface that enables users to directly compose generation intent in space through four complementary binding types: semantic, identity, text, and pixel, together with Text Specifications for individual elements and global appearance. Based on this interface, we develop Compo, a poster generation model adapted from a pretrained image editing model to understand Spatial Canvas inputs and Text Specifications. Compo supports both direct inference, where users explicitly construct the canvas, and agentic mode, where a high-level request is automatically translated into a planned Spatial Canvas. To train Compo, we develop a scalable pipeline that automatically constructs supervision data for different binding types and their combinations, enabling efficient adaptation without training a specialized poster generator from scratch. We further introduce a benchmark that evaluates adherence to individual binding types and their joint composition. Experiments show that Compo achieves stronger compositional controllability than both general-purpose image generation models and dedicated poster generation systems while maintaining high visual quality. By decoupling intent specification from visual generation, our work shifts poster generation from prompting toward composing.
Yitong Wang, Fangyun Wei, Jinjing Zhao +5
Fudan University · Microsoft Research · The University of Sydney +3
Automated academic poster generation aims to distill lengthy research papers into concise, visually coherent presentations. Existing Multimodal Large Language Models (MLLMs) based approaches, however, suffer from three critical limitations: low information density in full-paper inputs, excessive token consumption, and unreliable layout verification. We present EfficientPosterGen, an end-to-end framework that addresses these challenges through semantic-aware retrieval and token-efficient multimodal generation. EfficientPosterGen introduces three core innovations: (1) Semantic-aware Key Information Retrieval (SKIR), which constructs a semantic contribution graph to model inter-segment relationships and selectively preserves important content; (2) Visual-based Context Compression (VCC), which renders selected text segments into images to shift textual information into the visual modality, significantly reducing token usage while generating poster-ready bullet points; and (3) Agentless Layout Violation Detection (ALVD), a deterministic color-gradient-based algorithm that reliably detects content overflow and spatial sparsity without auxiliary MLLMs. Extensive experiments demonstrate that EfficientPosterGen achieves substantial improvements in token efficiency and layout reliability while maintaining high poster quality, offering a scalable solution for automated academic poster generation. Our code is available at https://github.com/vinsontang1/EfficientPosterGen-Code.
Wenxin Tang, Jingyu Xiao, Yanpei Gong +6
Tsinghua University, Beijing, China · The Chinese University of Hong Kong, Hong Kong, China · Harbin Institute of Technology, Harbin, China +4
Content-aware layout generation is a critical task in graphic design automation, focused on creating visually appealing arrangements of elements that seamlessly blend with a given background image. The variety of real-world applications makes it highly challenging to develop a single model capable of unifying the diverse range of input-constrained generation sub-tasks, such as those conditioned by element types, sizes, or their relationships. Current methods either address only a subset of these tasks or necessitate separate model parameters for different conditions, failing to offer a truly unified solution. In this paper, we propose UniLayDiff: a Unified Diffusion Transformer, that for the first time, addresses various content-aware layout generation tasks with a single, end-to-end trainable model. Specifically, we treat layout constraints as a distinct modality and employ Multi-Modal Diffusion Transformer framework to capture the complex interplay between the background image, layout elements, and diverse constraints. Moreover, we integrate relation constraints through fine-tuning the model with LoRA after pretraining the model on other tasks. Such a schema not only achieves unified conditional generation but also enhances overall layout quality. Extensive experiments demonstrate that UniLayDiff achieves state-of-the-art performance across from unconditional to various conditional generation tasks and, to the best of our knowledge, is the first model to unify the full range of content-aware layout generation tasks.
Zeyang Liu, Le Wang, Sanping Zhou +4
College of Artificial Intelligence, Xi’an Jiaotong University · Amazon.com, Inc. · Pixocial Technology