426 citations
- University of TübingenDE25 papers
- Max Planck Institute for Intelligent SystemsDE11 papers
- Max Planck Institute for Biological CyberneticsDE7 papers
- Max Planck SocietyDE6 papers
- University of LucerneCH3 papers
- University of Maryland, College ParkUS3 papers
- Max Planck Institute for Gravitational PhysicsDE2 papers
- Microsoft Research (United Kingdom)GB2 papers
- Tübingen AI Center2 papers
- University Hospital of BernCH2 papers
- University of BernCH2 papers
- University of BremenDE2 papers
37 papers
Stochastic wage suppression on gig platforms and how to organize against it
Ana-Andreea Stoica, Celestine Mendler-Duenner, Moritz Hardt
Digital labor platforms are increasingly used to procure human input, ranging from annotating data and red-teaming AI models, to ride-sharing and food delivery. A central concern i…
Flexible Gravitational-Wave Parameter Estimation with Transformers
Annalena Kofler, Maximilian Dax, Stephen R. Green +6
Gravitational-wave data analysis relies on accurate and efficient methods to extract physical information from noisy detector signals, yet the increasing rate and complexity of obs…
Subgroup Performance Analysis in Hidden Stratifications
Alceu Bissoto, Trung-Dung Hoang, Tim Flühmann +3
Machine learning (ML) models may suffer from significant performance disparities between patient groups. Identifying such disparities by monitoring performance at a granular level…
Real-time gravitational-wave inference for binary neutron stars using machine learning
Maximilian Dax, Stephen R. Green, Jonathan Gair +7
Mergers of binary neutron stars (BNSs) emit signals in both the gravitational-wave (GW) and electromagnetic (EM) spectra. Famously, the 2017 multi-messenger observation of GW170817…
ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents
Zhigen Li, Jianxiang Peng, Yanmeng Wang +13
Dialogue agents powered by Large Language Models (LLMs) show superior performance in various tasks. Despite the better user understanding and human-like responses, their **lack of…
Attri-Net: A Globally and Locally Inherently Interpretable Model for Multi-Label Classification Using Class-Specific Counterfactuals
Susu Sun, Stefano Woerner, Andreas Maier +2
Interpretability is crucial for machine learning algorithms in high-stakes medical applications. However, high-performing neural networks typically cannot explain their predictions…