# Less Is More: Balancing Positive and Negative Space in Visual Concept Blending

arXiv: https://arxiv.org/abs/2609.00476 · HTML: https://mlsanity.com/paper/2609.00476/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 58 references that are in the map.
- First posted on arXiv 31 Aug 2026.

## Builds on (most cited first, 8 of 8)

- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions](https://mlsanity.com/paper/2306.02224/) (2023)
- [viz2viz: Prompt-driven stylized visualization generation using a diffusion model](https://mlsanity.com/paper/2304.01919/) (2023)
- [PosterCopilot: Toward Layout Reasoning and Controllable Editing for Professional Graphic Design](https://mlsanity.com/paper/2512.04082/) (2025)
- [Visual Conceptual Blending with Large-scale Language and Vision Models](https://mlsanity.com/paper/2106.14127/) (2021)
- [GraphicBench: A Planning Benchmark for Graphic Design with Language Agents](https://mlsanity.com/paper/2504.11571/) (2025)
- [Stroke of Surprise: Progressive Semantic Illusions in Vector Sketching](https://mlsanity.com/paper/2602.12280/) (2026)
- [ChArtist: Generating Pictorial Charts with Unified Spatial and Subject Control](https://mlsanity.com/paper/2603.14209/) (2026)

## Abstract (arXiv)

Graphic designers often blend visual concepts to communicate multiple ideas within a single image, leveraging positive and negative space to create balance, emphasis, and aesthetic appeal. While computational methods have begun to support automatic concept blending, they largely overlook the role of spatial composition in the design. To address this gap, we present an automatic pipeline that explicitly applies positive and negative space throughout the blending process. Our approach first identifies plausible regions for concept integration by combining semantic reasoning from vision-language models with geometric constraints derived from real-world examples. Conditioned on these regions, the system generates blended compositions using a hybrid pixel-vector pipeline: diffusion-based inpainting produces a fast, coarse initialization, which is then refined through vector-based optimization at the point level to ensure structural coherence and balanced semantic expression. A multimodal agent orchestrates this process as a planner and evaluator, enabling iterative improvement and interpretable control. Through an evaluation using both baseline comparisons and a user study, we demonstrate greater expressiveness, creativity, and concept recognizability by effectively leveraging positive and negative space. We further demonstrate the generalizability of our approach across diverse applications, including controllable image and infographic generation.