activity
20242026
collaborators

8 papers

cs.LG2026

Task-Aware Calibration: Provably Optimal Decoding in LLMs

Tim Tomov, Dominik Fuchsgruber, Rajeev Verma +1

LLM decoding often relies on the model's predictive distribution to generate an output. Consequently, misalignment with respect to the true generating distribution leads to subopti…

cs.LG2026

Task-Awareness Improves LLM Generations and Uncertainty

Tim Tomov, Dominik Fuchsgruber, Stephan Günnemann

In many applications of LLMs, natural language responses often have an underlying structure such as representing discrete labels, numerical values, or graphs. Yet, existing decodin…

cs.LG2025

The Illusion of Certainty: Uncertainty Quantification for LLMs Fails under Ambiguity

Tim Tomov, Dominik Fuchsgruber, Tom Wollschläger +1

Accurate uncertainty quantification (UQ) in Large Language Models (LLMs) is critical for trustworthy deployment. While real-world language is inherently ambiguous, reflecting aleat…

cs.LG2025

Uncertainty Estimation for Heterophilic Graphs Through the Lens of Information Theory

Dominik Fuchsgruber, Tom Wollschläger, Johannes Bordne +1

While uncertainty estimation for graphs recently gained traction, most methods rely on homophily and deteriorate in heterophilic settings. We address this by analyzing message pass…

cs.CV2025

Prior2Former -- Evidential Modeling of Mask Transformers for Assumption-Free Open-World Panoptic Segmentation

Sebastian Schmidt, Julius Körner, Dominik Fuchsgruber +3

In panoptic segmentation, individual instances must be separated within semantic classes. As state-of-the-art methods rely on a pre-defined set of classes, they struggle with novel…

cs.LG2024

Graph Neural Networks for Edge Signals: Orientation Equivariance and Invariance

Dominik Fuchsgruber, Tim Poštuvan, Stephan Günnemann +1

Many applications in traffic, civil engineering, or electrical engineering revolve around edge-level signals. Such signals can be categorized as inherently directed, for example, t…