# FlexMUSE: Multimodal Unification and Semantics Enhancement Framework with Flexible interaction for Creative Writing

arXiv: https://arxiv.org/abs/2508.16230 · HTML: https://mlsanity.com/paper/2508.16230/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 37 references that are in the map.
- First posted on arXiv 22 Aug 2025.

## Builds on (most cited first, 21 of 21)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (2023)
- [Multimodal Chain-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2302.00923/) (2023)
- [Re3: Generating Longer Stories With Recursive Reprompting and Revision](https://mlsanity.com/paper/2210.06774/) (2022)
- [To Believe or Not to Believe Your LLM](https://mlsanity.com/paper/2406.02543/) (2024)
- [Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese](https://mlsanity.com/paper/2211.01335/) (2022)
- [Pretrained Language Models for Text Generation: A Survey](https://mlsanity.com/paper/2105.10311/) (2021)
- [StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation](https://mlsanity.com/paper/2209.06192/) (2022)
- [SEED-Story: Multimodal Long Story Generation with Large Language Model](https://mlsanity.com/paper/2407.08683/) (2024)
- [AutoStory: Generating Diverse Storytelling Images with Minimal Human Effort](https://mlsanity.com/paper/2311.11243/) (2023)
- [StoryGPT-V: Large Language Models as Consistent Story Visualizers](https://mlsanity.com/paper/2312.02252/) (2023)
- [VQA-GNN: Reasoning with Multimodal Knowledge via Graph Neural Networks for Visual Question Answering](https://mlsanity.com/paper/2205.11501/) (2022)
- [Bridging the Gap between 2D and 3D Visual Question Answering: A Fusion Approach for 3D VQA](https://mlsanity.com/paper/2402.15933/) (2024)
- [DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation](https://mlsanity.com/paper/2412.07589/) (2024)
- [GAN Computers Generate Arts? A Survey on Visual Arts, Music, and Literary Text Generation using Generative Adversarial Network](https://mlsanity.com/paper/2108.03857/) (2021)
- [LongStory: Coherent, Complete and Length Controlled Long story Generation](https://mlsanity.com/paper/2311.15208/) (2023)
- [LaDiC: Are Diffusion Models Really Inferior to Autoregressive Counterparts for Image-to-Text Generation?](https://mlsanity.com/paper/2404.10763/) (2024)
- [Let Storytelling Tell Vivid Stories: An Expressive and Fluent Multimodal Storyteller](https://mlsanity.com/paper/2403.07301/) (2024)

## Built on by (most cited first, 1 of 1)

- [TIP and Polish: Text-Image-Prototype Guided Multi-Modal Generation via Commonality-Discrepancy Modeling and Refinement](https://mlsanity.com/paper/2511.21698/) (2025)

## Abstract (arXiv)

Multi-modal creative writing (MMCW) aims to produce illustrated articles. Unlike common multi-modal generative (MMG) tasks such as storytelling or caption generation, MMCW is an entirely new and more abstract challenge where textual and visual contexts are not strictly related to each other. Existing methods for related tasks can be forcibly migrated to this track, but they require specific modality inputs or costly training, and often suffer from semantic inconsistencies between modalities. Therefore, the main challenge lies in economically performing MMCW with flexible interactive patterns, where the semantics between the modalities of the output are more aligned. In this work, we propose FlexMUSE with a T2I module to enable optional visual input. FlexMUSE promotes creativity and emphasizes the unification between modalities by proposing the modality semantic alignment gating (msaGate) to restrict the textual input. Besides, an attention-based cross-modality fusion is proposed to augment the input features for semantic enhancement. The modality semantic creative direct preference optimization (mscDPO) within FlexMUSE is designed by extending the rejected samples to facilitate the writing creativity. Moreover, to advance the MMCW, we expose a dataset called ArtMUSE which contains with around 3k calibrated text-image pairs. FlexMUSE achieves promising results, demonstrating its consistency, creativity and coherence.