MODIX: A Training-Free Multimodal Information-Driven Positional Index Scaling for Vision-Language Models

• URL: http://arxiv.org/abs/2604.12537v1
• Date: Tue, 14 Apr 2026 10:12:24 GMT
• Title: MODIX: A Training-Free Multimodal Information-Driven Positional Index Scaling for Vision-Language Models
• Abstract summary: Existing approaches uniformly assign positional indices to all tokens, overlooking variations in information density within and across modalities.<n>We propose MODIX, a training-free framework that dynamically adapts positional strides based on modality-specific contributions.<n>Experiments demonstrate that MODIX consistently improves multimodal reasoning and adaptively reallocates attention according to task-dependent information distributions.
• Score: 2.5982950439107064
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-Language Models (VLMs) have achieved remarkable progress in multimodal understanding, yet their positional encoding mechanisms remain suboptimal. Existing approaches uniformly assign positional indices to all tokens, overlooking variations in information density within and across modalities, which leads to inefficient attention allocation where redundant visual regions dominate while informative content is underrepresented. We identify positional granularity as an implicit resource and propose MODIX (Multimodal Information-Driven Positional IndeX Scaling), a training-free framework that dynamically adapts positional strides based on modality-specific contributions. MODIX jointly models intra-modal density via covariance-based entropy and inter-modal interaction via cross-modal alignment to derive unified scores, which rescale positional indices to allocate finer granularity to informative modalities while compressing redundant ones, without requiring any modification to model parameters or architecture. Experiments across diverse architectures and benchmarks demonstrate that MODIX consistently improves multimodal reasoning and adaptively reallocates attention according to task-dependent information distributions, suggesting that positional encoding should be treated as an adaptive resource in Transformers for multimodal sequence modeling.

Related papers

• MODAL: Multi-Modal Object Re-ID via Model-Driven Sparse Decoupling and Text-Image Differential Filtering [51.99452481869329]
  MODAL is a novel multi-modal object re-identification framework grounded in coupled sparse coding theory and differential suppression principles.<n>A core component of MODAL is a Multi-modal Feature Sparse Decoupling module, developed in a model-driven deep unrolling manner.<n>Benefiting from the principled feature disentanglement, MODAL naturally mitigates performance degradation in incomplete-modality scenarios.<n>Experiments on four datasets demonstrate that MODAL achieves state-of-the-art performance with superior transparency.
  arXiv  Detail & Related papers  (2026-08-15T07:41:10Z)
• LoMo: Local Modality Substitution for Deeper Vision-Language Fusion [10.837487434757882]
  Local Modality Substitution (LoMo) is a lightweight, architecture-agnostic data curation paradigm designed to provide supervision for cross-modal representational invariance between semantically equivalent text and image carriers.<n>LoMo significantly improves overall multimodal reasoning and yields deeper cross-modal fusion. Specifically, it delivers consistent gains across foundational models, improving over standard SFT by 2.67 points on LLaVA-Vision-1.5-8B and 2.82 points on Qwen3.5-9B.
  arXiv  Detail & Related papers  (2026-05-28T17:27:55Z)
• OMEGA: Optimized Multimodal Position Encoding Index Derivation with Global Adaptive Scaling for Vision-Language Models [4.809606597614951]
  Vision-Language Models (VLMs) have demonstrated strong performance across various tasks.<n>Position encoding plays a vital role in modeling both the sequential structure of textual information and the structure of visual information.<n>We propose OMEGA, a novel position encoding framework that employs Modality-Specific Position Scaling (MSPE) to assign positional indices.
  arXiv  Detail & Related papers  (2025-11-02T06:19:44Z)
• UniAlignment: Semantic Alignment for Unified Image Generation, Understanding, Manipulation and Perception [54.53657134205492]
  UniAlignment is a unified multimodal generation framework within a single diffusion transformer.<n>It incorporates both intrinsic-modal semantic alignment and cross-modal semantic alignment, thereby enhancing the model's cross-modal consistency and instruction-following robustness.<n>We present SemGen-Bench, a new benchmark specifically designed to evaluate multimodal semantic consistency under complex textual instructions.
  arXiv  Detail & Related papers  (2025-09-28T09:11:30Z)
• BiXFormer: A Robust Framework for Maximizing Modality Effectiveness in Multi-Modal Semantic Segmentation [55.486872677160015]
  We reformulate multi-modal semantic segmentation as a mask-level classification task.<n>We propose BiXFormer, which integrates Unified Modality Matching (UMM) and Cross Modality Alignment (CMA)<n> Experiments on both synthetic and real-world multi-modal benchmarks demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2025-06-04T08:04:58Z)
• MCFNet: A Multimodal Collaborative Fusion Network for Fine-Grained Semantic Classification [2.7936465461948945]
  Multimodal Collaborative Fusion Network (MCFNet) designed for fine-grained classification.<n>MCFNet architecture incorporates a regularized integrated fusion module that improves intra-modal feature representation.<n> multimodal decision classification module exploits inter-modal correlations and unimodal discriminative features.
  arXiv  Detail & Related papers  (2025-05-29T11:42:57Z)
• Reliable Multi-Modal Object Re-Identification via Modality-Aware Graph Reasoning [20.242422751083588]
  We propose to leverage a novel graph reasoning model, termed the Modality-aware Graph Reasoning Network (MGRNet)<n>We first construct modality-aware graphs to enhance the extraction of fine-grained local details.<n>We then employ the selective graph nodes swap operation to alleviate the adverse effects of low-quality local features.
  arXiv  Detail & Related papers  (2025-04-21T03:58:40Z)
• Distributional Vision-Language Alignment by Cauchy-Schwarz Divergence [83.15764564701706]
  We propose a novel framework that performs vision-language alignment by integrating Cauchy-Schwarz divergence with mutual information.<n>We find that the CS divergence seamlessly addresses the InfoNCE's alignment-uniformity conflict and serves complementary roles with InfoNCE.<n> Experiments on text-to-image generation and cross-modality retrieval tasks demonstrate the effectiveness of our method on vision-language alignment.
  arXiv  Detail & Related papers  (2025-02-24T10:29:15Z)
• Modality Prompts for Arbitrary Modality Salient Object Detection [57.610000247519196]
  This paper delves into the task of arbitrary modality salient object detection (AM SOD) It aims to detect salient objects from arbitrary modalities, eg RGB images, RGB-D images, and RGB-D-T images. A novel modality-adaptive Transformer (MAT) will be proposed to investigate two fundamental challenges of AM SOD.
  arXiv  Detail & Related papers  (2024-05-06T11:02:02Z)
• Multimodal Informative ViT: Information Aggregation and Distribution for Hyperspectral and LiDAR Classification [25.254816993934746]
  Multimodal Informative Vit (MIVit) is a system with an innovative information aggregate-distributing mechanism. MIVit reduces redundancy in the empirical distribution of each modality's separate and fused features. Our results show that MIVit's bidirectional aggregate-distributing mechanism is highly effective.
  arXiv  Detail & Related papers  (2024-01-06T09:53:33Z)
• Multi-Modal Mutual Information Maximization: A Novel Approach for Unsupervised Deep Cross-Modal Hashing [73.29587731448345]
  We propose a novel method, dubbed Cross-Modal Info-Max Hashing (CMIMH) We learn informative representations that can preserve both intra- and inter-modal similarities. The proposed method consistently outperforms other state-of-the-art cross-modal retrieval methods.
  arXiv  Detail & Related papers  (2021-12-13T08:58:03Z)

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.