Query-based Cross-Modal Projector Bolstering Mamba Multimodal LLM

• URL: http://arxiv.org/abs/2606.04719v1
• Date: Wed, 03 Jun 2026 10:56:56 GMT
• Title: Query-based Cross-Modal Projector Bolstering Mamba Multimodal LLM
• Abstract summary: The Selective Scan Structured State-Space Model, or Mamba, addresses this computational challenge effectively.<n>This paper explores a query-based cross-modal projector designed to bolster Mamba's efficiency for vision-language modeling.
• Score: 34.72878578414079
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The Transformer's quadratic complexity with input length imposes an unsustainable computational load on large language models (LLMs). In contrast, the Selective Scan Structured State-Space Model, or Mamba, addresses this computational challenge effectively. This paper explores a query-based cross-modal projector designed to bolster Mamba's efficiency for vision-language modeling by compressing visual tokens based on input through the cross-attention mechanism. This innovative projector also removes the need for manually designing the 2D scan order of original image features when converting them into an input sequence for Mamba LLM. Experimental results across various vision-language understanding benchmarks show that the proposed cross-modal projector enhances Mamba-based multimodal LLMs, boosting both performance and throughput.

Related papers

• ABMAMBA: Multimodal Large Language Model with Aligned Hierarchical Bidirectional Scan for Efficient Video Captioning [11.388109553982089]
  We focus on video captioning by fully open multimodal large language models (MLLMs)<n>ABMamba is a fully open MLLM with linear computational complexity that enables the scalable processing of video sequences.<n>On standard video captioning benchmarks such as VATEX and MSR-VTT, ABMamba demonstrates competitive performance compared to typical MLLMs.
  arXiv  Detail & Related papers  (2026-04-09T09:58:56Z)
• From One-to-One to Many-to-Many: Dynamic Cross-Layer Injection for Deep Vision-Language Fusion [91.35078719566472]
  Vision-Language Models (VLMs) create a severe visual feature bottleneck by using a crude, asymmetric connection.<n>We introduce Cross-Layer Injection (CLI), a novel and lightweight framework that forges a dynamic many-to-many bridge between the two modalities.
  arXiv  Detail & Related papers  (2026-01-15T18:59:10Z)
• MirrorMamba: Towards Scalable and Robust Mirror Detection in Videos [64.87702843502889]
  We propose a new effective and scalable video mirror detection method, called MirrorMamba.<n>Our approach leverages multiple cues to adapt to diverse conditions, incorporating perceived depth, correspondence and optical.<n> Notably, this work marks the first successful application of the Mamba-based architecture in the field of mirror detection.
  arXiv  Detail & Related papers  (2025-11-10T05:18:14Z)
• Trajectory-aware Shifted State Space Models for Online Video Super-Resolution [57.87099307245989]
  This paper presents a novel online VSR method based on Trajectory-aware Shifted SSMs (TS-Mamba)<n>TS-Mamba first constructs the trajectories within a video to select the most similar tokens from the previous frames.<n>Our TS-Mamba achieves state-of-the-art performance in most cases and over 22.7% reduction complexity (in MACs)
  arXiv  Detail & Related papers  (2025-08-14T08:42:15Z)
• SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-Rewards [55.99492656542475]
  We propose textbfSUDER (textbfSelf-improving textbfUnified LMMs with textbfDual stextbfElf-textbfRewards), a framework reinforcing the understanding and generation capabilities of LMMs.
  arXiv  Detail & Related papers  (2025-06-09T17:38:45Z)
• LEO: Boosting Mixture of Vision Encoders for Multimodal Large Language Models [9.660892239615364]
  This work explores fusion strategies of visual tokens for hybrid MLLMs, leading to the design of LEO.<n>Leo is a novel MLLM with a dual-branch vision encoder framework that incorporates a post-adaptation fusion strategy and adaptive tiling.<n>We show that LEO can be adapted to the specialized domain of autonomous driving without altering the model architecture or training recipe.
  arXiv  Detail & Related papers  (2025-01-13T00:29:55Z)
• MobileMamba: Lightweight Multi-Receptive Visual Mamba Network [51.33486891724516]
  Previous research on lightweight models has primarily focused on CNNs and Transformer-based designs. We propose the MobileMamba framework, which balances efficiency and performance. MobileMamba achieves up to 83.6% on Top-1, surpassing existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-11-24T18:01:05Z)
• EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical Alignment [39.870809905905325]
  We propose Empowering Multi-modal Mamba with Structural and Hierarchical Alignment (EMMA) to extract fine-grained visual information. Our model shows lower latency than other Mamba-based MLLMs and is nearly four times faster than transformer-based MLLMs of similar scale during inference.
  arXiv  Detail & Related papers  (2024-10-08T11:41:55Z)
• ML-Mamba: Efficient Multi-Modal Large Language Model Utilizing Mamba-2 [4.30176340351235]
  We introduce ML-Mamba, a multimodal language model, which utilizes the latest and efficient Mamba-2 model for inference. We replace the Transformer-based backbone with a pre-trained Mamba-2 model and explore methods for integrating 2D visual selective scanning mechanisms into multimodal learning.
  arXiv  Detail & Related papers  (2024-07-29T09:38:15Z)
• VL-Mamba: Exploring State Space Models for Multimodal Learning [22.701028299912398]
  In this work, we propose VL-Mamba, a multimodal large language model based on state space models. Specifically, we first replace the transformer-based backbone language model such as LLama or Vicuna with the pre-trained Mamba language model.
  arXiv  Detail & Related papers  (2024-03-20T13:48:50Z)
• Lumen: Unleashing Versatile Vision-Centric Capabilities of Large Multimodal Models [87.47400128150032]
  We propose a novel LMM architecture named Lumen, a Large multimodal model with versatile vision-centric capability enhancement. Lumen first promotes fine-grained vision-language concept alignment. Then the task-specific decoding is carried out by flexibly routing the shared representation to lightweight task decoders.
  arXiv  Detail & Related papers  (2024-03-12T04:13:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.