Program

Accepted Workshop Presentations

• Rahul Nair, Bastian Lipka, Elizabeth M. Daly. Policy-as-Logic for Robust Reasoning over Rules

• Amy Rafferty, Rishi Ramaesh, Ajitha Rajan. Clinically Aware Synthetic Image Generation for Concept Coverage in Chest X-ray Models

• Julian Müller, Jan-Patrick Osterloh, Eike Möhlmann. Robust Translation of Natural Language into Traffic Sequence Charts and Co-Simulation with Human Driver Models

• Aradhana Nayak, Mussadiq Nazeer, Peng Wang, Feng Liu. GUI agent: Guided Exploration of User-Sensitive Screens

• Yingjie Wang, Xiangyu Yin, Julian Müller. Uncertainty-Aware Retrieval for Robust Scenario Composition: A GFlowNet–RAG Framework with Subset-Simulation Calibration

• Alexandru-Stefan Morosanu, Valerian Cecan, Laura Erhan, Stefan Daniel Achirei. Distinguishing AI-Generated Music from Edited Audio as a Hard-Negative Robustness Task

• Arooj Arif, Alexandros Koliousis, Tobias Hartung, Elena Botoeva. TestNav: Pareto-Guided Search for Compositional Robustness Testing

• Hikaru Matsuoka. Safety-Prefix Pinning for Production KV-Cache Quantization: Measurement, Mechanism, and a Multilingual Defense

• Kunwar Zaid, Amit Sangroya, Jyotsana Khatri, Vikas Kumar. Trustworthiness of LLMs in Cross-Lingual Clinical Summarization: An Empirical Study on Indian Languages

• Zhiguo Tao, He Zhihua. BIEV: A Differentiable Framework for Precise Property Manipulation of Biological Entities

• Nitesh Kumar. DocConf: Document-Grounded Confidence Estimation for Robust LLM Field Extraction

• Kulin Nikita, Zhuravlev Viktor, Khairullin Artur, Sergey Muravyov, Ilya Makarov, Daniil Sukhorukov. From Monolithic to Modular: Segment-level Automatic Prompt Optimization

• Deep Kumar Ganguly, Jan Kretinsky. Quantifying Risk Under Evolving Uncertainty: Belief-Dependent Robustness for Safe Sequential Decision Making