# Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference

arXiv: https://arxiv.org/abs/2403.14520 · HTML: https://mlsanity.com/paper/2403.14520/

## Key facts

- Cited by 97 papers in the map (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 45 of its 61 references that are in the map.
- First posted on arXiv 21 Mar 2024.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)
- State-space sequence models (S4, Mamba) / [Vision Mamba backbones](https://mlsanity.com/ssm/vision-mamba-backbones/)

## Builds on (most cited first, 30 of 45)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [VizWiz Grand Challenge: Answering Visual Questions from Blind People](https://mlsanity.com/paper/1802.08218/) (2018)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [Simplified State Space Layers for Sequence Modeling](https://mlsanity.com/paper/2208.04933/) (2022)
- [PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel](https://mlsanity.com/paper/2304.11277/) (2023)
- [TinyLlama: An Open-Source Small Language Model](https://mlsanity.com/paper/2401.02385/) (2024)
- [LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model](https://mlsanity.com/paper/2304.15010/) (2023)
- [OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models](https://mlsanity.com/paper/2308.01390/) (2023)

## Built on by (most cited first, 30 of 97)

- [MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection](https://mlsanity.com/paper/2404.06564/) (2024)
- [PointVLA: Injecting the 3D World into Vision-Language-Action Models](https://mlsanity.com/paper/2503.07511/) (2025)
- [RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation](https://mlsanity.com/paper/2406.04339/) (2024)
- [Efficient Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2405.10739/) (2024)
- [Mamba-360: Survey of State Space Models as Transformer Alternative for Long Sequence Modelling: Methods, Applications, and Challenges](https://mlsanity.com/paper/2404.16112/) (2024)
- [State Space Model for New-Generation Network Alternative to Transformers: A Survey](https://mlsanity.com/paper/2404.09516/) (2024)
- [Vision Mamba: A Comprehensive Survey and Taxonomy](https://mlsanity.com/paper/2405.04404/) (2024)
- [VLAS: Vision-Language-Action Model With Speech Instructions For Customized Robot Manipulation](https://mlsanity.com/paper/2502.13508/) (2025)
- [A Survey on Visual Mamba](https://mlsanity.com/paper/2404.15956/) (2024)
- [ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement Learning](https://mlsanity.com/paper/2505.07395/) (2025)
- [SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning](https://mlsanity.com/paper/2505.12448/) (2025)
- [MBQ: Modality-Balanced Quantization for Large Vision-Language Models](https://mlsanity.com/paper/2412.19509/) (2024)
- [Visual Mamba: A Survey and New Outlooks](https://mlsanity.com/paper/2404.18861/) (2024)
- [A Survey of Mamba](https://mlsanity.com/paper/2408.01129/) (2024)
- [Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models](https://mlsanity.com/paper/2405.15574/) (2024)
- [Unveiling the Ignorance of MLLMs: Seeing Clearly, Answering Incorrectly](https://mlsanity.com/paper/2406.10638/) (2024)
- [MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods](https://mlsanity.com/paper/2501.13484/) (2025)
- [Quamba: A Post-Training Quantization Recipe for Selective State Space Models](https://mlsanity.com/paper/2410.13229/) (2024)
- [CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction](https://mlsanity.com/paper/2412.06782/) (2024)
- [MoRE: Unlocking Scalability in Reinforcement Learning for Quadruped Vision-Language-Action Models](https://mlsanity.com/paper/2503.08007/) (2025)
- [Matten: Video Generation with Mamba-Attention](https://mlsanity.com/paper/2405.03025/) (2024)
- [Geolocation with Real Human Gameplay Data: A Large-Scale Dataset and Human-Like Reasoning Framework](https://mlsanity.com/paper/2502.13759/) (2025)
- [BIMBA: Selective-Scan Compression for Long-Range Video Question Answering](https://mlsanity.com/paper/2503.09590/) (2025)
- [MVGamba: Unify 3D Content Generation as State Space Sequence Modeling](https://mlsanity.com/paper/2406.06367/) (2024)
- [The Evolution of Multimodal Model Architectures](https://mlsanity.com/paper/2405.17927/) (2024)
- [Mambular: A Sequential Model for Tabular Deep Learning](https://mlsanity.com/paper/2408.06291/) (2024)
- [Hybrid Mamba for Few-Shot Segmentation](https://mlsanity.com/paper/2409.19613/) (2024)
- [ObjectVLA: End-to-End Open-World Object Manipulation Without Demonstration](https://mlsanity.com/paper/2502.19250/) (2025)
- [Mamba in Vision: A Comprehensive Survey of Techniques and Applications](https://mlsanity.com/paper/2410.03105/) (2024)
- [ActiveVLA: Injecting Active Perception into Vision-Language-Action Models for Precise 3D Robotic Manipulation](https://mlsanity.com/paper/2601.08325/) (2026)

## Abstract (arXiv)

In recent years, the application of multimodal large language models (MLLM) in various fields has achieved remarkable success. However, as the foundation model for many downstream tasks, current MLLMs are composed of the well-known Transformer network, which has a less efficient quadratic computation complexity. To improve the efficiency of such basic models, we propose Cobra, a linear computational complexity MLLM. Specifically, Cobra integrates the efficient Mamba language model into the visual modality. Moreover, we explore and study various modal fusion schemes to create an effective multi-modal Mamba. Extensive experiments demonstrate that (1) Cobra achieves extremely competitive performance with current computationally efficient state-of-the-art methods, e.g., LLaVA-Phi, TinyLLaVA, and MobileVLM v2, and has faster speed due to Cobra's linear sequential modeling. (2) Interestingly, the results of closed-set challenging prediction benchmarks show that Cobra performs well in overcoming visual illusions and spatial relationship judgments. (3) Notably, Cobra even achieves comparable performance to LLaVA with about 43% of the number of parameters. We will make all codes of Cobra open-source and hope that the proposed method can facilitate future research on complexity problems in MLLM. Our project page is available at: https://sites.google.com/view/cobravlm.