32 papers
Creativity from Friction: Human-AI Interaction for Exploratory Structural Design
Ricardo Maia Avelino, Rita Sevastjanova, Tom Van Mele +2
AI agents that generate final answers based on user input often do not meet the needs of creative fields. Fields such as structural design and architecture need interactive systems…
GeoXplain: On-the-Fly Visual Explanations for Weather Foundation Models
Clemens Walter Koprolin, Leonardo Trentini, Benedikt Soja +2
Weather and climate foundation models produce high-dimensional forecasts whose learned relationships are difficult to inspect with static plots alone. GeoXplain is an interactive P…
From Interaction to Intent: Inferring User Objectives from Provenance Logs
Steffen Holter, Tobias Stähle, Arpit Narechania +1
The ability to automatically infer analytic intent from user interaction histories could enable interactive AI systems to proactively assist users during exploratory data analysis.…
GEMS -- Guided Evolutionary Molecule Design for Sustainable Chemicals
Coelina Robinson, Franziska Weissbach, Kjell Jorner +2
Designing safe and sustainable chemicals is critical to combat chemical pollution in our environment. Computational and AI-assisted methods have been developed to aid de novo molec…
Building Fast, Evaluating Slow: Pipeline Choices Dominate Autointerpretability Score Variance
Sinie van der Ben, Neele Roch, Anna Hedström +1
Cross-paper comparison of sparse autoencoder (SAE) interpretability often relies on autointerpretability scores. In this evaluation pipeline, a language model (LM) explains each fe…
Where Do Models Find Happiness? Emotion Vectors in Open-Source LLMs
Sinie van der Ben, Raphaël Baur, Yannick Metz +1
Recent work identified emotion vectors in Claude Sonnet 4.5, which are internal representations that encode emotion concepts, causally influence behavior, and exhibit geometry mirr…