Hidden Layer Interaction: A Technique to Explore the Material of Generative AI
Research Output:
Conference Article in Proceeding or Book/Report chapter
Article in proceedings
Peer-reviewOpen access
Publication Information
Output type
Research Output:
Conference Article in Proceeding or Book/Report chapter
Article in proceedings
Peer-reviewOriginal language
EnglishPages from-to (Number of pages)
Pages 1913-1927Publication milestones
- Published - 2025
Publication status
Published - 2025
Publisher
Association for Computing Machinery, United StatesISBN (Print)
979-8-4007-1485-6/2025/07ISBN (Electronic)
979-8-4007-1485-6/2025/07Publication IDs
- Scopus: 105020660810
Host publication title
ACM DIS '25: Proceedings of the 2025 ACM Designing Interactive Systems ConferenceAbstract
This pictorial describes the process of developing an interaction technique for directly engaging with the hidden layers of a generative AI model for image synthesis. First, we give some background to generative AI in HCI, arguing that current interaction techniques prevent us from directly interacting with the material of AI, foreclosing its use in design. Drawing on inspiration from the Computer Science field of feature visualization, we investigate the materiality of our prototype, a GAN model trained to generate fashion imagery, and show how Hidden Layer Interaction offers an alternative to standard prompting. In doing so, we illustrate how this change in approach leads to new forms of interaction with the internal semantics of generative AI, and demonstrate how one might use Hidden Layer Interaction to engage with AI as a material in design.
Publication metrics
PlumX
Citations
10
Captures
8
Access to documents
Final published version
License:CC BY-NC-ND, opens in new tab
Related Event
Title
ACM Conference on Designing Interactive Systems
Event type
ConferenceLinks
Degree of recognition
International eventDate
05/07/2025 - 09/07/2025Location
MadeiraPortugal
