# GeoPID: Decomposing and Steering Visual Information in Vision-Language Models

arXiv: https://arxiv.org/abs/2610.08401 · HTML: https://mlsanity.com/paper/2610.08401/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 28 of its 72 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 28 of 28)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension](https://mlsanity.com/paper/2307.16125/) (2023)
- [SmolVLM: Redefining small and efficient multimodal models](https://mlsanity.com/paper/2504.05299/) (2025)
- [SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models](https://mlsanity.com/paper/2504.11468/) (2025)
- [GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation](https://mlsanity.com/paper/2406.13743/) (2024)
- [Reducing Hallucinations in Vision-Language Models via Latent Space Steering](https://mlsanity.com/paper/2410.15778/) (2024)
- [MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources](https://mlsanity.com/paper/2509.21268/) (2025)
- [One RL to See Them All: Visual Triple Unified Reinforcement Learning](https://mlsanity.com/paper/2505.18129/) (2025)
- [A Closer Look at Multimodal Representation Collapse](https://mlsanity.com/paper/2505.22483/) (2025)
- [Information Plane Analysis of Deep Neural Networks via Matrix-Based Renyi's Entropy and Tensor Kernels](https://mlsanity.com/paper/1909.11396/) (2019)
- [MINT: Mitigating Hallucinations in Large Vision-Language Models via Token Reduction](https://mlsanity.com/paper/2502.00717/) (2025)
- [Mitigating Hallucination in Large Vision-Language Models through Aligning Attention Distribution to Information Flow](https://mlsanity.com/paper/2505.14257/) (2025)
- [How Vision Becomes Language: A Layer-wise Information-Theoretic Analysis of Multimodal Reasoning](https://mlsanity.com/paper/2602.15580/) (2026)
- [Dynamic Multimodal Activation Steering for Hallucination Mitigation in Large Vision-Language Models](https://mlsanity.com/paper/2602.21704/) (2026)
- [Hierarchical and Multimodal Data for Daily Activity Understanding](https://mlsanity.com/paper/2504.17696/) (2025)
- [Multivariate Extension of Matrix-based Renyi's α-order Entropy Functional](https://mlsanity.com/paper/1808.07912/) (2018)
- [Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition](https://mlsanity.com/paper/2606.00959/) (2026)
- [AdaDim: Dimensionality Adaptation for SSL Representational Dynamics](https://mlsanity.com/paper/2505.12576/) (2025)
- [A Comprehensive Information-Decomposition Analysis of Large Vision-Language Models](https://mlsanity.com/paper/2603.29676/) (2026)
- [VEGAS: Mitigating Hallucinations in Large Vision-Language Models via Vision-Encoder Attention Guided Adaptive Steering](https://mlsanity.com/paper/2512.12089/) (2025)
- [Aligning What Vision-Language Models See and Perceive with Adaptive Information Flow](https://mlsanity.com/paper/2604.15809/) (2026)
- [Curing Semantic Drift: A Dynamic Approach to Grounding Generation in Large Vision-Language Models](https://mlsanity.com/paper/2506.21509/) (2025)
- [Information Router for Mitigating Modality Dominance in Vision-Language Models](https://mlsanity.com/paper/2604.16264/) (2026)
- [GEASS: Gated Evidence-Adaptive Selective Caption Trust for Vision-Language Models](https://mlsanity.com/paper/2605.01733/) (2026)

## Abstract (arXiv)

While recent vision-language models (VLMs) have shown outstanding performance across diverse applications, they tend to under-use visual information and over-rely on textual context. In this work, we propose textscGeoPID, a training-free framework that analyzes multimodal information within VLMs from a geometric perspective. textscGeoPID decomposes information into Redundant, Modality-Unique, and Synergistic components through the geometric relationships between visual and textual representation subspaces. Through an extensive analysis across 22 VLMs and 14 benchmarks, we confirm that correct predictions exhibit stronger vision-unique components when questions strongly require visual grounding. Building on this geometric analysis, we introduce a targeted intervention technique that selectively amplifies visual representations along the vision-unique subspace during inference. As a result, visual grounding capabilities were enhanced without any additional model parameter updates, achieving an average relative accuracy gain of 7.63%.