2 papers
cs.HC2026
Unpacking Interpretability: Human-Centered Criteria for Optimal Combinatorial Solutions
Dominik Pegler, Frank Jäkel, David Steyrl +2
Algorithmic support systems often return optimal solutions that are hard to understand. Effective human-algorithm collaboration, however, requires interpretability. When machine so…
cs.CV2026
SpiderNets: Vision Models Predict Human Fear From Aversive Images
Dominik Pegler, David Steyrl, Mengfan Zhang +4
Phobias are common and impairing, and exposure therapy, which involves confronting patients with fear-provoking visual stimuli, is the most effective treatment. Scalable computeriz…