# Selective State Space Memory for Large Vision-Language Models

arXiv: https://arxiv.org/abs/2412.09875 · HTML: https://mlsanity.com/paper/2412.09875/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Visual token pruning and efficiency, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 12 of its 22 references that are in the map.
- First posted on arXiv 13 Dec 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Visual token pruning and efficiency](https://mlsanity.com/mllm/visual-token-pruning-and-efficiency/)
- State-space sequence models (S4, Mamba) / [Vision Mamba backbones](https://mlsanity.com/ssm/vision-mamba-backbones/)

## Builds on (most cited first, 12 of 12)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [DeepSeek-VL: Towards Real-World Vision-Language Understanding](https://mlsanity.com/paper/2403.05525/) (2024)
- [MoE-LLaVA: Mixture of Experts for Large Vision-Language Models](https://mlsanity.com/paper/2401.15947/) (2024)
- [InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output](https://mlsanity.com/paper/2407.03320/) (2024)
- [Rethinking Visual Dependency in Long-Context Reasoning for Large Vision-Language Models](https://mlsanity.com/paper/2410.19732/) (2024)
- [Visual Mamba: A Survey and New Outlooks](https://mlsanity.com/paper/2404.18861/) (2024)
- [MambaLRP: Explaining Selective State Space Sequence Models](https://mlsanity.com/paper/2406.07592/) (2024)
- [TextHawk2: A Large Vision-Language Model Excels in Bilingual OCR and Grounding with 16x Fewer Tokens](https://mlsanity.com/paper/2410.05261/) (2024)
- [MemoryMamba: Memory-Augmented State Space Model for Defect Recognition](https://mlsanity.com/paper/2405.03673/) (2024)
- [InsectMamba: Insect Pest Classification with State Space Model](https://mlsanity.com/paper/2404.03611/) (2024)
- [A Mamba Foundation Model for Time Series Forecasting](https://mlsanity.com/paper/2411.02941/) (2024)
- [PEANuT: Parameter-Efficient Adaptation with Weight-aware Neural Tweakers](https://mlsanity.com/paper/2410.01870/) (2024)

## Abstract (arXiv)

Large Vision-Language Models (LVLMs) have demonstrated remarkable performance across a wide range of multimodal tasks. However, fine-tuning these models for domain-specific applications remains a computationally intensive challenge. This paper introduces State Space Memory Integration (SSMI), a novel approach for efficient fine-tuning of LVLMs. By integrating lightweight Mamba-based state space modules into the LVLM architecture, SSMI captures long-range dependencies and injects task-specific visual and sequential patterns effectively. Unlike traditional fine-tuning methods, SSMI requires only a fraction of the model's parameters to be updated, making it computationally efficient and scalable. Experiments on benchmark datasets, including COCO Captioning, VQA, and Flickr30k, demonstrate that SSMI achieves state-of-the-art performance while maintaining robustness and generalization capabilities. Comprehensive analysis further validates the advantages of SSMI in terms of efficiency, adaptability, and interpretability, positioning it as a compelling solution for fine-tuning large-scale vision-language models.