To balance task performance and computational cost, agentic workflows can use a lower-cost model for execution and selectively consult a stronger model. In such executor-advisor systems, the executor decides when to seek advice, making escalation depend on self-assessment, although current language models struggle to d...
Pascal Sowietzki, Steffen Holter, Yannick Metz et al.· 0 citations
The Visual Analytics Context Protocol (VACP), a framework designed to make VA applications "agent-ready" that extends generic protocols by explicitly exposing application state, available interactions, and mechanisms for direct execution, is introduced.
Tobias Stähle, Péter Ferenc Gyarmati, Thilo Spinner et al.· arXiv.org· 3 citations
GNN-VIEW exposes the graph's information pathways, allowing model developers to debug the graph structure before training and after training, GNN-VIEW uses attribution-based explainability to reveal which input features are used by the trained model for a given forecast.
Alessandro Lucatelli, Ferdinand Unterhuber, Katharina Krenzer et al.· 0 citations
People commonly express preferences through soft attributes such as is interesting,''which are difficult to operationalize for computational preference modeling. Latent representations can obscure how such attributes are interpreted, limiting transparency and user control. We formalize softness as the diversity of vali...
Steffen Holter, Rita Sevastjanova, Michaela Benk et al.· 0 citations
This work introduces STRIDE, the first framework for evaluating context alignment between scenario descriptions and pedestrian trajectories, and believes that the STRIDE framework provides a first step toward principled evaluation of context-aligned pedestrian trajectory generation.
Wan-Chun Ni, Tao Qi, Leonel Aguilar et al.· 0 citations
This work presents marimo-lens, an extension to the reactive Python notebook marimo for grounded human-agent analysis that connects a human's marked output and note to its producing cell and relevant contributing computation, giving the agent computational context for the request.
Péter Ferenc Gyarmati, Trevor Manz, Dominik Moritz et al.· 0 citations
MIVAIS is presented, a dual-layered research platform designed to abstract the structural complexities of mixed-initiative VA and evaluates the framework's expressiveness and efficiency through expert case studies with HCI and VA researchers, demonstrating how MIVAIS effectively lowers the barrier to prototyping and ev...
Tobias Stähle, Simone Schneider, Rita Sevastjanova et al.· 0 citations
It is found that methodological variance collectively exceeds architectural variance across all metrics and tested models, suggesting that cross-paper comparisons based on autointerpretability scores may reflect pipeline differences rather than architectural differences, with implications for the ongoing debate on SAE...
Sinie van der Ben, Neele Roch, Anna Hedström et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.