# AGSwap: Overcoming Category Boundaries in Object Fusion via Adaptive Group Swapping

arXiv: https://arxiv.org/abs/2509.18699 · HTML: https://mlsanity.com/paper/2509.18699/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 48 references that are in the map.
- First posted on arXiv 23 Sep 2025.

## Builds on (most cited first, 30 of 31)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://mlsanity.com/paper/2310.04378/) (2023)
- [Muse: Text-To-Image Generation via Masked Generative Transformers](https://mlsanity.com/paper/2301.00704/) (2023)
- [Compositional Visual Generation with Composable Diffusion Models](https://mlsanity.com/paper/2206.01714/) (2022)
- [Evaluating Text-to-Visual Generation with Image-to-Text Generation](https://mlsanity.com/paper/2404.01291/) (2024)
- [An Edit Friendly DDPM Noise Space: Inversion and Manipulations](https://mlsanity.com/paper/2304.06140/) (2023)
- [FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models](https://mlsanity.com/paper/2412.08629/) (2024)
- [Taming Rectified Flow for Inversion and Editing](https://mlsanity.com/paper/2411.04746/) (2024)
- [Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion](https://mlsanity.com/paper/2310.03502/) (2023)
- [Inversion-Free Image Editing with Natural Language](https://mlsanity.com/paper/2312.04965/) (2023)
- [TurboEdit: Text-Based Image Editing Using Few-Step Diffusion Models](https://mlsanity.com/paper/2408.00735/) (2024)
- [MagicMix: Semantic Mixing with Diffusion Models](https://mlsanity.com/paper/2210.16056/) (2022)
- [DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling](https://mlsanity.com/paper/2412.00759/) (2024)
- [ConceptLab: Creative Concept Generation using VLM-Guided Diffusion Prior Constraints](https://mlsanity.com/paper/2308.02669/) (2023)
- [NoiseCollage: A Layout-Aware Text-to-Image Diffusion Model Based on Noise Cropping and Merging](https://mlsanity.com/paper/2403.03485/) (2024)
- [Factorized Diffusion: Perceptual Illusions by Noise Decomposition](https://mlsanity.com/paper/2404.11615/) (2024)
- [Separate-and-Enhance: Compositional Finetuning for Text2Image Diffusion Models](https://mlsanity.com/paper/2312.06712/) (2023)
- [PAIR-Diffusion: A Comprehensive Multimodal Object-Level Image Editor](https://mlsanity.com/paper/2303.17546/) (2023)
- [TP2O: Creative Text Pair-to-Object Generation using Balance Swap-Sampling](https://mlsanity.com/paper/2310.01819/) (2023)
- [PartCraft: Crafting Creative Objects by Parts](https://mlsanity.com/paper/2407.04604/) (2024)
- [Enhancing Creative Generation on Stable Diffusion-based Models](https://mlsanity.com/paper/2503.23538/) (2025)
- [Novel Object Synthesis via Adaptive Text-Image Harmony](https://mlsanity.com/paper/2410.20823/) (2024)
- [Multitwine: Multi-Object Compositing with Text and Layout Control](https://mlsanity.com/paper/2502.05165/) (2025)
- [PTDiffusion: Free Lunch for Generating Optical Illusion Hidden Pictures with Phase-Transferred Diffusion Model](https://mlsanity.com/paper/2503.06186/) (2025)
- [MoEdit: On Learning Quantity Perception for Multi-object Image Editing](https://mlsanity.com/paper/2503.10112/) (2025)

## Built on by (most cited first, 2 of 2)

- [A Creative Agent is Worth a 64-Token Template](https://mlsanity.com/paper/2603.17895/) (2026)
- [Self-Creative Text-to-Object Generation using Semantic-Aware Spatial Weighting](https://mlsanity.com/paper/2605.19554/) (2026)

## Abstract (arXiv)

Fusing cross-category objects to a single coherent object has gained increasing attention in text-to-image (T2I) generation due to its broad applications in virtual reality, digital media, film, and gaming. However, existing methods often produce biased, visually chaotic, or semantically inconsistent results due to overlapping artifacts and poor integration. Moreover, progress in this field has been limited by the absence of a comprehensive benchmark dataset. To address these problems, we propose Adaptive Group Swapping (AGSwap), a simple yet highly effective approach comprising two key components: (1) Group-wise Embedding Swapping, which fuses semantic attributes from different concepts through feature manipulation, and (2) Adaptive Group Updating, a dynamic optimization mechanism guided by a balance evaluation score to ensure coherent synthesis. Additionally, we introduce Cross-category Object Fusion (COF), a large-scale, hierarchically structured dataset built upon ImageNet-1K and WordNet. COF includes 95 superclasses, each with 10 subclasses, enabling 451,250 unique fusion pairs. Extensive experiments demonstrate that AGSwap outperforms state-of-the-art compositional T2I methods, including GPT-Image-1 using simple and complex prompts.