Probing the "Conscious" Mind: Selective Access and Global Workspace in Vision-Language Models
Probing the "Conscious" Mind: Selective Access and Global Workspace in Vision-Language Models
Multimodal Concept Lens (MC-Lens) reveals the accessibility and selective access mechanisms of VLM concepts by mapping the intermediate states of visual and language encoders to a shared semantic space. Experiments show that the accessed conceptual information participates in downstream computation and reasoning, and it is found that there are differences in the development of cross-modal alignment and selective access.
Published on Nov 19
Authors:
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.
View arXiv page View PDF Add to collection
Get this paper in your agent:
hf papers read 2611.26590
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2611.26590 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2611.26590 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2611.26590 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
Source: Hugging Face Daily Papers · huggingface.co