cs.AINov 19, 2026

Probing the "Conscious" Mind: Selective Access and Global Workspace in Vision-Language Models

Authors: Jiahao Huang, Jun Wang

Organizations: Imperial College London, UK · University College London, UK

Abstract

Vision-language models (VLMs) integrate visual and textual information, but their outputs do not reveal internal concept representations. Global workspace theory (GWT) proposes that information is selected from parallel brain processes, integrated in a shared workspace, and made available to specialised processes. We introduce the Multimodal Concept Lens (MC-Lens), a multimodal Jacobian lens, to study these functions in VLM concept processing. Its vision encoder and language decoder lenses map intermediate states to a shared semantic space defined by the decoder's output vocabulary to compare concept accessibility across modalities. MC-Lens supports internal concept interventions to examine the role of accessed concepts in downstream computation. (i) Accessibility and selective access. Multimodal concept information is readable in intermediate states and selectively accessible as tasks require. We extend "readout carriers" from one name token to a token set to better capture and express concept information and support counterfactual experiments. (ii) Concepts in downstream computation. Counterfactual experiments show that accessed concept information participates in downstream computation and reasoning. (iii) Development of cross-modal alignment and selective access. We develop two J-space metrics tracking the development of cross-modal concept alignment more clearly than hidden state cosine in controlled VLM training. The experiment also shows that reliable selective access develops later than concept accessibility. (iv) Shared functions across models. Across VLM families and sizes, we find shared patterns of concept accessibility, query-dependent selectivity and cross-task intervention effects despite differences in internal organisation. These findings offer an experimental basis to study GWT in multimodal artificial systems and how it can guide cross-modal alignment improvements.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Circuit Tracing in Vision-Language Models: Understanding the Internal Mechanisms of Multimodal Thinking

    Feb 23, 2026Jingcheng Yang, Tianhu Xiong, Shengyi Qian +2VLM InterpretabilityVLM Reasoning

  2. Did I See It or Think It? Probing Reality Monitoring in Vision-Language Models with Concept Injection

    Nov 6, 2026Tina Khezresmaeilzadeh, Seyedarmin Azizi, Mehdi Kamal +1Faithfulness in VLMsHallucination Detection in VLMs

  3. Extraction and Analysis of Multimodal Concepts in Vision Language Models through Sparse Autoencoders

    Jun 19, 2026Sergio Lanza, Jae Hee Lee, Stefan WermterVision-Language ModelsVLM Interpretability