From One-to-One to Many-to-Many: Dynamic Cross-Layer Injection for Deep Vision-Language Fusion

• URL: http://arxiv.org/abs/2601.10710v1
• Date: Thu, 15 Jan 2026 18:59:10 GMT
• Title: From One-to-One to Many-to-Many: Dynamic Cross-Layer Injection for Deep Vision-Language Fusion
• Authors: Cheng Chen, Yuyu Guo, Pengpeng Zeng, Jingkuan Song, Peng Di, Hang Yu, Lianli Gao,
• Abstract summary: 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.
• Score: 91.35078719566472
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-Language Models (VLMs) create a severe visual feature bottleneck by using a crude, asymmetric connection that links only the output of the vision encoder to the input of the large language model (LLM). This static architecture fundamentally limits the ability of LLMs to achieve comprehensive alignment with hierarchical visual knowledge, compromising their capacity to accurately integrate local details with global semantics into coherent reasoning. To resolve this, we introduce Cross-Layer Injection (CLI), a novel and lightweight framework that forges a dynamic many-to-many bridge between the two modalities. CLI consists of two synergistic, parameter-efficient components: an Adaptive Multi-Projection (AMP) module that harmonizes features from diverse vision layers, and an Adaptive Gating Fusion (AGF) mechanism that empowers the LLM to selectively inject the most relevant visual information based on its real-time decoding context. We validate the effectiveness and versatility of CLI by integrating it into LLaVA-OneVision and LLaVA-1.5. Extensive experiments on 18 diverse benchmarks demonstrate significant performance improvements, establishing CLI as a scalable paradigm that unlocks deeper multimodal understanding by granting LLMs on-demand access to the full visual hierarchy.

Related papers

• Rethinking Visual Information Processing in Multimodal LLMs [9.660144531857933]
  We present LLaViT - Large Language Models as extended Vision Transformers.<n>We show that LLaViT significantly outperforms the baseline LLaVA method on a multitude of benchmarks.
  arXiv  Detail & Related papers  (2025-11-13T13:36:30Z)
• BcQLM: Efficient Vision-Language Understanding with Distilled Q-Gated Cross-Modal Fusion [6.8723394189831035]
  Large language models pose challenges for deployment in resource-constrained environments.<n>We propose a lightweight MLLM framework for end-to-end visual question answering.<n>Our proposed approach centres on BreezeCLIP, a compact yet powerful vision-language optimised for efficient multimodal understanding.
  arXiv  Detail & Related papers  (2025-09-10T16:09:49Z)
• LLaVA-SP: Enhancing Visual Representation with Visual Spatial Tokens for MLLMs [4.478610052538001]
  We propose LLaVA-SP, which only adds six spatial visual tokens to the original visual tokens to enhance the visual representation.<n>We present two model variants: LLaVA-SP-Cropping, which focuses on detail features through progressive cropping, and LLaVA-SP-Pooling, which captures global semantics through adaptive pooling.
  arXiv  Detail & Related papers  (2025-07-01T07:20:11Z)
• Instruction-Guided Fusion of Multi-Layer Visual Features in Large Vision-Language Models [50.98559225639266]
  We investigate the contributions of visual features from different encoder layers using 18 benchmarks spanning 6 task categories.<n>Our findings reveal that multilayer features provide complementary strengths with varying task dependencies, and uniform fusion leads to suboptimal performance.<n>We propose the instruction-guided vision aggregator, a module that dynamically integrates multi-layer visual features based on textual instructions.
  arXiv  Detail & Related papers  (2024-12-26T05:41:31Z)
• LLaVA-UHD v2: an MLLM Integrating High-Resolution Semantic Pyramid via Hierarchical Window Transformer [110.39467860530819]
  Vision transformers (ViTs) are widely employed in multimodal large language models (MLLMs) for visual encoding.<n>We present LLaVA-UHD v2, an MLLM with advanced perception abilities by introducing a well-designed vision-language projector.<n>Hiwin transformer enhances MLLM's ability to capture diverse multi-modal visual granularities, by incorporating our constructed high-resolution semantic pyramid.
  arXiv  Detail & Related papers  (2024-12-18T14:07:46Z)
• Liquid: Language Models are Scalable and Unified Multi-modal Generators [112.71734051183726]
  Liquid is an auto-regressive generation paradigm that seamlessly integrates visual comprehension and generation.<n>Unlike previous multimodal large language model (MLLM), Liquid achieves this integration using a single large language model.<n>For the first time, Liquid uncovers a scaling law that performance drop unavoidably brought by the unified training of visual and language tasks.
  arXiv  Detail & Related papers  (2024-12-05T16:48:16Z)
• ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning [38.26304604660713]
  ADEM-VL is an efficient vision-language method that tunes models based on pretrained large language models. Our framework surpasses existing methods by an average accuracy of 0.77% on ScienceQA dataset.
  arXiv  Detail & Related papers  (2024-10-23T11:31:06Z)
• EMMA: Efficient Visual Alignment in Multi-Modal LLMs [56.03417732498859]
  EMMA is a lightweight cross-modality module designed to efficiently fuse visual and textual encodings.<n>EMMA boosts performance across multiple tasks by up to 9.3% while significantly improving robustness against hallucinations.
  arXiv  Detail & Related papers  (2024-10-02T23:00:31Z)
• SEA: Supervised Embedding Alignment for Token-Level Visual-Textual Integration in MLLMs [31.88022265176855]
  Supervised Embedding Alignment (SEA) is a token-level supervision alignment method that enables more precise visual-text alignment during pretraining.<n>Our comprehensive analyses reveal critical insights into the adapter's role in multimodal integration, and extensive experiments demonstrate that SEA consistently improves performance across various model sizes.
  arXiv  Detail & Related papers  (2024-08-21T17:58:02Z)
• INF-LLaVA: Dual-perspective Perception for High-Resolution Multimodal Large Language Model [71.50973774576431]
  We propose a novel MLLM, INF-LLaVA, designed for effective high-resolution image perception. We introduce a Dual-perspective Cropping Module (DCM), which ensures that each sub-image contains continuous details from a local perspective. Second, we introduce Dual-perspective Enhancement Module (DEM) to enable the mutual enhancement of global and local features.
  arXiv  Detail & Related papers  (2024-07-23T06:02:30Z)
• CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion [58.15403987979496]
  CREMA is a generalizable, highly efficient, and modular modality-fusion framework for video reasoning.<n>We propose a novel progressive multimodal fusion design supported by a lightweight fusion module and modality-sequential training strategy.<n>We validate our method on 7 video-language reasoning tasks assisted by diverse modalities, including VideoQA and Video-Audio/3D/Touch/Thermal QA.
  arXiv  Detail & Related papers  (2024-02-08T18:27:22Z)
• All in One: Exploring Unified Vision-Language Tracking with Multi-Modal Alignment [39.54689489555342]
  Current vision-injected (VL) tracking framework consists of three parts, ie a visual feature extractor, a language feature extractor, and a fusion model.<n>We propose an All-in-One framework, which learns joint feature extraction and interaction by adopting a unified transformer backbone.
  arXiv  Detail & Related papers  (2023-07-07T03:51:21Z)

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.