Stateful Cross-layer Vision Modulation

• URL: http://arxiv.org/abs/2603.00655v1
• Date: Sat, 28 Feb 2026 13:57:19 GMT
• Title: Stateful Cross-layer Vision Modulation
• Authors: Ying Liu, Yudong Han, Kean Shi, Liyuan Pan,
• Abstract summary: multimodal large language models (MLLMs) widely adopt multi-layer visual feature fusion to enhance visual representation.<n>Existing approaches typically perform static concatenation or weighted aggregation after visual encoding, without intervening in the representation formation process itself.<n>We propose a cross-layer memory-modulated vision framework(SCVM) to address these limitations.
• Score: 19.730096071316876
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent multimodal large language models (MLLMs) widely adopt multi-layer visual feature fusion to enhance visual representation. However, existing approaches typically perform static concatenation or weighted aggregation after visual encoding, without intervening in the representation formation process itself. As a result, fine-grained details from early layers may be progressively suppressed during hierarchical abstraction. Moreover, directly introducing shallow-layer features into the language model often leads to semantic distribution mismatch with the visual feature space that the LLM's cross-attention layers were pretrained on, which typically requires additional adaptation or fine-tuning of the LLM. To address these limitations, we revisit visual representation learning from the perspective of representation evolution control and propose a cross-layer memory-modulated vision framework(SCVM). Specifically, we introduce a recursively updated cross-layer memory state inside the vision encoder to model long-range inter-layer dependencies. We further design a layer-wise feedback modulation mechanism that refreshes token representations at each layer based on the accumulated memory, thereby structurally regulating the representation evolution trajectory. In addition, we incorporate an auxiliary semantic alignment objective that explicitly supervises the final memory state, encouraging progressive compression and reinforcement of task-relevant information. Experimental results on multiple visual question answering and hallucination evaluation benchmarks demonstrate that SCVM achieves consistent performance improvements without expanding visual tokens, introducing additional vision encoders, or modifying or fine-tuning the language model.

Related papers

• Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigation [51.743225614196774]
  Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language reasoning.<n>They remain vulnerable to hallucination, where generated content deviates from visual evidence.<n>Recent vision enhancement methods attempt to address this issue by reinforcing visual tokens during decoding.<n>We propose Adaptive Visual Reinforcement (AIR), a training-free framework for MLLMs.
  arXiv  Detail & Related papers  (2026-02-27T14:18:51Z)
• Unleashing the Intrinsic Visual Representation Capability of Multimodal Large Language Models [58.91911788912665]
  We propose Latent Visual Reconstruction (LaVer), a novel training framework that facilitates MLLMs in learning more discrimi visual representations.<n>Our method offers direct visual activation to MLLMs, which exhibit increased visual attention allocation, indicating enhanced utilization of visual information.
  arXiv  Detail & Related papers  (2025-12-06T04:20:13Z)
• ParaUni: Enhance Generation in Unified Multimodal Model with Reinforcement-driven Hierarchical Parallel Information Interaction [55.21514454560188]
  Unified multimodal models significantly improve visual generation by combining vision-grained models (VLMs) with diffusion models.<n>Existing methods struggle to fully balance sufficient interaction and flexible implementation due to vast representation difference.<n>We propose textbfParaUni, which extracts features from variants VLM's layers in a textbfParallel way for comprehensive information interaction.
  arXiv  Detail & Related papers  (2025-12-05T04:41:57Z)
• Multi-Modal Interpretability for Enhanced Localization in Vision-Language Models [2.984679075401059]
  This paper presents the Multi-Modal Explainable Learning framework, designed to enhance the interpretability of vision-language models.<n>Our approach processes features at multiple semantic levels to capture relationships between image regions at different granularities.<n>We show that by incorporating semantic relationship information into gradient-based attribution maps, MMEL produces more focused and contextually aware visualizations.
  arXiv  Detail & Related papers  (2025-09-17T18:18:59Z)
• Dynamic Embedding of Hierarchical Visual Features for Efficient Vision-Language Fine-Tuning [5.85033069870214]
  We propose an efficient vision-language fine-tuning method based on dynamic embedding and fusion of hierarchical visual features.<n>By fine-tuning only a small number of parameters, DEHVF achieves precise alignment and complement of cross-modal information.
  arXiv  Detail & Related papers  (2025-08-25T03:57:46Z)
• Cross-Layer Discrete Concept Discovery for Interpreting Language Models [13.842670153893977]
  Cross-layer VQ-VAE is a framework that uses vector quantization to map representations across layers.<n>Our approach uniquely combines top-k temperature-based sampling during quantization with EMA codebook updates.
  arXiv  Detail & Related papers  (2025-06-24T22:43:36Z)
• FOCUS: Unified Vision-Language Modeling for Interactive Editing Driven by Referential Segmentation [55.01077993490845]
  Recent Large Vision Language Models (LVLMs) demonstrate promising capabilities in unifying visual understanding and generative modeling.<n>We introduce FOCUS, a unified LVLM that integrates segmentation-aware perception and controllable object-centric generation within an end-to-end framework.
  arXiv  Detail & Related papers  (2025-06-20T07:46:40Z)
• How Visual Representations Map to Language Feature Space in Multimodal LLMs [9.880509106657009]
  We study the mechanism by which vision-language models (VLMs) achieve alignment of visual and linguistic representations.<n>By keeping the language model frozen, we ensure it maintains its original language representations without adaptation to visual data.<n>We reveal the layer-wise progression through which visual representations gradually align with language feature representations, converging in middle-to-later layers.
  arXiv  Detail & Related papers  (2025-06-13T17:34:05Z)
• Lifting the Veil on Visual Information Flow in MLLMs: Unlocking Pathways to Faster Inference [28.24397677839652]
  Multimodal large language models (MLLMs) improve performance on vision-language tasks by integrating visual features from pre-trained vision encoders into large language models.<n>How MLLMs process and utilize visual information remains unclear.<n>We propose Hierarchical Modality-Aware Pruning (HiMAP), a plug-and-play inference acceleration method that dynamically prunes image tokens at specific layers, reducing computational costs by approximately 65% without sacrificing performance.
  arXiv  Detail & Related papers  (2025-03-17T12:31:23Z)
• Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent [72.1517476116743]
  Recent MLLMs have shown emerging visual understanding and reasoning abilities after being pre-trained on large-scale multimodal datasets.<n>Existing approaches, such as direct fine-tuning and continual learning methods, fail to explicitly address this issue.<n>We introduce a novel perspective leveraging effective rank to quantify the degradation of visual representation forgetting.<n>We propose a modality-decoupled gradient descent (MDGD) method that regulates gradient updates to maintain the effective rank of visual representations.
  arXiv  Detail & Related papers  (2025-02-17T12:26:34Z)
• 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)
• RefSAM: Efficiently Adapting Segmenting Anything Model for Referring Video Object Segmentation [53.4319652364256]
  This paper presents the RefSAM model, which explores the potential of SAM for referring video object segmentation. Our proposed approach adapts the original SAM model to enhance cross-modality learning by employing a lightweight Cross-RValModal. We employ a parameter-efficient tuning strategy to align and fuse the language and vision features effectively.
  arXiv  Detail & Related papers  (2023-07-03T13:21:58Z)

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.