9 citations · 9 across the 5 of their papers we have counts for
6 papers
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…
Visual Fingerprints for LLM Generation Comparison
Amal Alnouri, Andreas Hinterreiter, Christina Humer +2
Large language model (LLM) outputs arise from complex interactions among prompts, system instructions, model parameters, and architecture. We refer to specific configurations of th…
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…
GFlowState: Visualizing the Training of Generative Flow Networks Beyond the Reward
Florian Holeczek, Andreas Hinterreiter, Alex Hernandez-Garcia +2
We present GFlowState, a visual analytics system designed to illuminate the training process of Generative Flow Networks (GFlowNets or GFNs). GFlowNets are a probabilistic framewor…
Catalyst GFlowNet for electrocatalyst design: A hydrogen evolution reaction case study
Lena Podina, Christina Humer, Alexandre Duval +7
Efficient and inexpensive energy storage is essential for accelerating the adoption of renewable energy and ensuring a stable supply, despite fluctuations in sources such as wind a…
ParaDime: A Framework for Parametric Dimensionality Reduction
Andreas Hinterreiter, Christina Humer, Bernhard Kainz +1
ParaDime is a framework for parametric dimensionality reduction (DR). In parametric DR, neural networks are trained to embed high-dimensional data items in a low-dimensional space…