4 papers
SketchXplain: Intuitive Visual Explanations of Image Classifiers with Sketches
Wencan Zhang, Mario Michelessa, Xuejun Zhao +1
Saliency map visualizations explain image-based AI predictions by pointing to regions, but these are often unintuitive and semantically unclear, leaving an interpretability gap. We…
How Many Different Outputs Can a Transformer Generate?
Maxime Meyer, Mario Michelessa, Caroline Chaux +1
We study how we can leverage only a handful of characteristics of a transformer's architecture to closely predict the number of different sequences it can output, both qualitativel…
Memory Limitations of Prompt Tuning in Transformers
Maxime Meyer, Mario Michelessa, Caroline Chaux +1
Despite the empirical success of prompt tuning in adapting pretrained language models to new tasks, theoretical analyses of its capabilities remain limited. Existing theoretical wo…
Varif.ai to Vary and Verify User-Driven Diversity in Scalable Image Generation
M. Michelessa, J. Ng, C. Hurter +1
Diversity in image generation is essential to ensure fair representations and support creativity in ideation. Hence, many text-to-image models have implemented diversification mech…