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

Vision Language models (VLMs) have demonstrated strong performance across a wide range of benchmarks, yet they often suffer from modality dominance, where predictions rely disproportionately on a single modality. Prior approaches primarily address this issue by steering model's attention allocation, implicitly assuming that all modalities provide sufficient information. However, attention only determines where the model focuses, and cannot enrich information that is missing or ambiguous. In the real world, input modalities often differ in information density and their signal-to-noise ratios. In such cases, simply adjusting model's attention does not resolve the underlying lack of information. In this paper, we propose MoIR: Multi-modal Information Router, an information-level fusion method that explicitly reduces information disparity prior to fusion. MoIR identifies less informative tokens and routes complementary information from a stronger modality, constructing information-dense token representations before they are processed by a large language model. By modifying information availability, MoIR enables reliable shifts in modality dominance, even when one modality is degraded. We evaluate MoIR on three widely used multi-modal benchmarks across multiple model backbones. Experimental results show that MoIR consistently demonstrates more balanced modality contribution, and improves robustness and downstream performance, particularly even under modality degradation. These findings demonstrate that explicitly modifying cross-modal information is an effective and complementary strategy for mitigating modality dominance in multi-modal reasoning models.

When a multimodal Transformer answers a visual question, is the prediction driven by visual evidence, linguistic reasoning, or genuinely fused cross-modal computation -- and how does this structure evolve across layers? We address this question with a layer-wise framework based on Partial Information Decomposition (PID) that decomposes the predictive information at each Transformer layer into redundant, vision-unique, language-unique, and synergistic components. To make PID tractable for high-dimensional neural representations, we introduce PID Flow, a pipeline combining dimensionality reduction, normalizing-flow Gaussianization, and closed-form Gaussian PID estimation. Applying this framework to LLaVA-1.5-7B and LLaVA-1.6-7B across six GQA reasoning tasks, we uncover a consistent modal transduction pattern: visual-unique information peaks early and decays with depth, language-unique information surges in late layers to account for roughly 82% of the final prediction, and cross-modal synergy remains below 2%. This trajectory is highly stable across model variants (layer-wise correlations $>$0.96) yet strongly task-dependent, with semantic redundancy governing the detailed information fingerprint. To establish causality, we perform targeted Image$\rightarrow$Question attention knockouts and show that disrupting the primary transduction pathway induces predictable increases in trapped visual-unique information, compensatory synergy, and total information cost -- effects that are strongest in vision-dependent tasks and weakest in high-redundancy tasks. Together, these results provide an information-theoretic, causal account of how vision becomes language in multimodal Transformers, and offer quantitative guidance for identifying architectural bottlenecks where modality-specific information is lost.

Diffusion-based multimodal large language models (dMLLMs) decode by iteratively predicting tokens at multiple masked positions in parallel. This turns each decoding step into a position-selection problem: the model must choose not only which predictions are reliable in isolation, but also which positions should be committed together as context for later decoding steps. Existing confidence-based decoding ranks masked positions independently and commits the top-K positions, largely ignoring whether the committed tokens provide complementary visual grounding. We identify a step-level limitation of this strategy in multimodal settings: high-confidence tokens selected in the same step can rely on overlapping visual grounding, introducing visual redundancy among the committed tokens and leaving less complementary visual grounding available for later decoding. To quantify this effect, we introduce the Visual Redundancy Index (VRI), which measures visual grounding overlap among tokens committed in parallel. To control this redundancy during decoding, we propose Visual-Redundancy-Controlled Decoding (VRCD), a training-free inference-time decoding method that uses token-to-image attention to prioritize visually complementary positions. Across diverse multimodal benchmarks, VRCD reduces visual redundancy and remaining-position entropy with modest runtime overhead. In longer decoding experiments, it also achieves relative accuracy gains of up to 18.8% on M^3CoT and 6.9% on MMBench over confidence-based decoding. Code is available at https://github.com/infiniteYuanyl/VRCD.