A Comprehensive Information-Decomposition Analysis of Large Vision-Language Models

• URL: http://arxiv.org/abs/2603.29676v1
• Date: Tue, 31 Mar 2026 12:32:29 GMT
• Title: A Comprehensive Information-Decomposition Analysis of Large Vision-Language Models
• Abstract summary: Large vision-language models (LVLMs) achieve impressive performance, yet their internal decision-making processes remain opaque.<n>We introduce a novel framework using partial information decomposition (PID) to quantitatively measure the "information spectrum" of LVLMs.<n>Our analysis reveals two key results: (i) two task regimes (synergy-driven vs. knowledge-driven) and (ii) two stable, contrasting family-level strategies (fusion-centric vs. language-centric)
• Score: 24.18585407100395
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large vision-language models (LVLMs) achieve impressive performance, yet their internal decision-making processes remain opaque, making it difficult to determine if the success stems from true multimodal fusion or from reliance on unimodal priors. To address this attribution gap, we introduce a novel framework using partial information decomposition (PID) to quantitatively measure the "information spectrum" of LVLMs -- decomposing a model's decision-relevant information into redundant, unique, and synergistic components. By adapting a scalable estimator to modern LVLM outputs, our model-agnostic pipeline profiles 26 LVLMs on four datasets across three dimensions -- breadth (cross-model & cross-task), depth (layer-wise information dynamics), and time (learning dynamics across training). Our analysis reveals two key results: (i) two task regimes (synergy-driven vs. knowledge-driven) and (ii) two stable, contrasting family-level strategies (fusion-centric vs. language-centric). We also uncover a consistent three-phase pattern in layer-wise processing and identify visual instruction tuning as the key stage where fusion is learned. Together, these contributions provide a quantitative lens beyond accuracy-only evaluation and offer insights for analyzing and designing the next generation of LVLMs. Code and data are available at https://github.com/RiiShin/pid-lvlm-analysis .

Related papers

• Decouple to Generalize: Context-First Self-Evolving Learning for Data-Scarce Vision-Language Reasoning [41.523848964102]
  Recent vision-language models (VLMs) achieve remarkable reasoning through reinforcement learning (RL)<n>RL provides a feasible solution for realizing continuous self-evolving large vision-language models (LVLMs) in the era of experience.<n>Existing strategies such as synthetic data and self-rewarding mechanisms suffer from limited distributions and alignment difficulties.<n>We propose DoGe, a dual-decoupling framework that guides models to first learn from context rather than problem solving.
  arXiv  Detail & Related papers  (2025-12-07T13:17:31Z)
• Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting [70.83781268763215]
  Vision-language models (VLMs) have achieved impressive performance across diverse multimodal tasks by leveraging large-scale pre-training.<n>VLMs face unique challenges such as cross-modal feature drift, parameter interference due to shared architectures, and zero-shot capability erosion.<n>This survey aims to serve as a comprehensive and diagnostic reference for researchers developing lifelong vision-language systems.
  arXiv  Detail & Related papers  (2025-08-06T09:03:10Z)
• Multimodal Behavioral Patterns Analysis with Eye-Tracking and LLM-Based Reasoning [12.054910727620154]
  Eye-tracking data reveals valuable insights into users' cognitive states but is difficult to analyze due to its structured, non-linguistic nature.<n>This paper presents a multimodal human-AI collaborative framework designed to enhance cognitive pattern extraction from eye-tracking signals.
  arXiv  Detail & Related papers  (2025-07-24T09:49:53Z)
• MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings [75.0617088717528]
  MoCa is a framework for transforming pre-trained VLM backbones into effective bidirectional embedding models.<n>MoCa consistently improves performance across MMEB and ViDoRe-v2 benchmarks, achieving new state-of-the-art results.
  arXiv  Detail & Related papers  (2025-06-29T06:41:00Z)
• Why Do Open-Source LLMs Struggle with Data Analysis? A Systematic Empirical Study [55.09905978813599]
  Large Language Models (LLMs) hold promise in automating data analysis tasks.<n>Yet open-source models face significant limitations in these kinds of reasoning-intensive scenarios.<n>In this work, we investigate strategies to enhance the data analysis capabilities of open-source LLMs.
  arXiv  Detail & Related papers  (2025-06-24T17:04:23Z)
• LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning [39.54891426369773]
  Trade-offs between model size, architecture, and performance remain underexplored.<n>In this paper, we introduce LLaVA-MORE, a new family of MLLMs that integrates recent language models with diverse visual backbones.<n>To ensure fair comparisons, we employ a unified training protocol applied consistently across all architectures.
  arXiv  Detail & Related papers  (2025-03-19T18:10:12Z)
• X2-DFD: A framework for eXplainable and eXtendable Deepfake Detection [55.77552681618732]
  X2-DFD is an eXplainable and eXtendable framework based on multimodal large-language models (MLLMs) for deepfake detection.<n>The first stage, Model Feature Assessment, systematically evaluates the detectability of forgery-related features for the MLLM.<n>The second stage, Explainable dataset Construction, consists of two key modules: Strong Feature Strengthening and Weak Feature Supplementing.<n>The third stage, Fine-tuning and Inference, involves fine-tuning the MLLM on the constructed dataset and deploying it for final detection and explanation.
  arXiv  Detail & Related papers  (2024-10-08T15:28:33Z)
• Large Vision-Language Models as Emotion Recognizers in Context Awareness [14.85890824622433]
  Context-aware emotion recognition (CAER) is a complex and significant task that requires perceiving emotions from various contextual cues. Previous approaches primarily focus on designing sophisticated architectures to extract emotional cues from images. This paper systematically explore the potential of leveraging Large Vision-Language Models (LVLMs) to empower the CAER task.
  arXiv  Detail & Related papers  (2024-07-16T01:28:06Z)
• Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models [73.40350756742231]
  Visually-conditioned language models (VLMs) have seen growing adoption in applications such as visual dialogue, scene understanding, and robotic task planning. Despite the volume of new releases, key design decisions around image preprocessing, architecture, and optimization are under-explored.
  arXiv  Detail & Related papers  (2024-02-12T18:21:14Z)
• Improving Open Information Extraction with Large Language Models: A Study on Demonstration Uncertainty [52.72790059506241]
  Open Information Extraction (OIE) task aims at extracting structured facts from unstructured text. Despite the potential of large language models (LLMs) like ChatGPT as a general task solver, they lag behind state-of-the-art (supervised) methods in OIE tasks.
  arXiv  Detail & Related papers  (2023-09-07T01:35:24Z)

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.