Abstract
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.
| Original language | English |
|---|---|
| Title of host publication | ACM DIS '25: Proceedings of the 2025 ACM Designing Interactive Systems Conference |
| Publisher | Association for Computing Machinery |
| Publication date | 2025 |
| Pages | 1913-1927 |
| ISBN (Print) | 979-8-4007-1485-6/2025/07 |
| ISBN (Electronic) | 979-8-4007-1485-6/2025/07 |
| Publication status | Published - 2025 |
| Event | ACM Conference on Designing Interactive Systems - Madeira, Portugal Duration: 5 Jul 2025 → 9 Jul 2025 https://dl.acm.org/doi/proceedings/10.1145/3715336 https://dblp.org/db/conf/ACMdis/ACMdis2025.html |
Conference
| Conference | ACM Conference on Designing Interactive Systems |
|---|---|
| Country/Territory | Portugal |
| City | Madeira |
| Period | 05/07/2025 → 09/07/2025 |
| Internet address |
Keywords
- Generative AI
- Interpretability
- Interaction Design
Fingerprint
Dive into the research topics of 'Hidden Layer Interaction: A Technique to Explore the Material of Generative AI'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver