# Bringing The Consistency Gap: Explicit Structured Memory for Interleaved Image-Text Generation

arXiv: https://arxiv.org/abs/2510.10969 · HTML: https://mlsanity.com/paper/2510.10969/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 26 of its 29 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)

## Builds on (most cited first, 26 of 26)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models](https://mlsanity.com/paper/2403.06764/) (2024)
- [NExT-GPT: Any-to-Any Multimodal LLM](https://mlsanity.com/paper/2309.05519/) (2023)
- [Generative Multimodal Models are In-Context Learners](https://mlsanity.com/paper/2312.13286/) (2023)
- [Image Generation from Scene Graphs](https://mlsanity.com/paper/1804.01622/) (2018)
- [Neurosymbolic AI: The 3rd Wave](https://mlsanity.com/paper/2012.05876/) (2020)
- [The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence](https://mlsanity.com/paper/2002.06177/) (2020)
- [A Comprehensive Survey of Scene Graphs: Generation and Application](https://mlsanity.com/paper/2104.01111/) (2021)
- [MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer](https://mlsanity.com/paper/2401.10208/) (2024)
- [Controllable Text-to-Image Generation with GPT-4](https://mlsanity.com/paper/2305.18583/) (2023)
- [Diffusion-Based Scene Graph to Image Generation with Masked Contrastive Pre-Training](https://mlsanity.com/paper/2211.11138/) (2022)
- [MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models](https://mlsanity.com/paper/2410.10139/) (2024)
- [OpenING: A Comprehensive Benchmark for Judging Open-ended Interleaved Image-Text Generation](https://mlsanity.com/paper/2411.18499/) (2024)
- [SearchLVLMs: A Plug-and-Play Framework for Augmenting Large Vision-Language Models by Searching Up-to-Date Internet Knowledge](https://mlsanity.com/paper/2405.14554/) (2024)
- [Neuro-Symbolic Generative Diffusion Models for Physically Grounded, Robust, and Safe Generation](https://mlsanity.com/paper/2506.01121/) (2025)
- [Unlocking the Potential of Generative AI through Neuro-Symbolic Architectures: Benefits and Limitations](https://mlsanity.com/paper/2502.11269/) (2025)
- [Image Regeneration: Evaluating Text-to-Image Model via Generating Identical Image with Multimodal Large Language Models](https://mlsanity.com/paper/2411.09449/) (2024)
- [Why Settle for One? Text-to-ImageSet Generation and Evaluation](https://mlsanity.com/paper/2506.23275/) (2025)

## Abstract (arXiv)

Existing Vision Language Models (VLMs) often struggle to preserve logic, entity identity, and artistic style during extended, interleaved image-text interactions. We identify this limitation as "Multimodal Context Drift", which stems from the inherent tendency of implicit neural representations to decay or become entangled over long sequences. To bridge this gap, we propose IUT-Plug, a model-agnostic Neuro-Symbolic Structured State Tracking mechanism. Unlike purely neural approaches that rely on transient attention maps, IUT-Plug introduces the Image Understanding Tree (IUT) as an explicit, persistent memory module. The framework operates by (1) parsing visual scenes into hierarchical symbolic structures (entities, attributes, and relationships); (2) performing incremental state updates to logically lock invariant properties while modifying changing elements; and (3) guiding generation through topological constraints. We evaluate our approach on a novel benchmark comprising 3,000 human-annotated samples. Experimental results demonstrate that IUT-Plug effectively mitigates context drift, achieving significantly higher consistency scores compared to unstructured text-prompting baselines. This confirms that explicit symbolic grounding is essential for maintaining robust long-horizon consistency in multimodal generation.