7 papers
SIR: Structured Image Representations for Explainable Robot Learning
Paul Mattes, Jan Schwab, Jens Bosch +5
Existing robot policies based on learned visual embeddings lack explicit structure and are sensitive to visual distractions. Thus, the representations that drive their behaviour ar…
SPARC: Reliable Spatial Annotations from Robot Demonstrations at Scale
Nils Blank, Paul Mattes, Maximilian Xiling Li +5
This work introduces Spatial Annotations from Robot Demonstrations with Reliability Calibration (SPARC), a risk-aware framework that automatically labels robot demonstrations with…
DuoBench: A Reproducible Benchmark for Bimanual Manipulation in Simulation and the Real World
Tobias Jülg, Seongjin Bien, Simon Hilber +7
Bimanual robot systems substantially expand manipulation capabilities, but coordinating two arms introduces additional control complexity and failure modes that are not well captur…
An Overview of Prototype Formulations for Interpretable Deep Learning
Maximilian Xiling Li, Korbinian Franz Rudolf, Paul Mattes +2
Prototypical part networks offer interpretable alternatives to black-box deep learning models by learning visual prototypes for classification. This work provides a comprehensive a…
Planning in a recurrent neural network that plays Sokoban
Mohammad Taufeeque, Philip Quirke, Maximilian Li +4
Planning is essential for solving complex tasks, yet the internal mechanisms underlying planning in neural networks remain poorly understood. Building on prior work, we analyze a r…
Endless Jailbreaks with Bijection Learning
Brian R. Y. Huang, Maximilian Li, Leonard Tang
Despite extensive safety measures, LLMs are vulnerable to adversarial inputs, or jailbreaks, which can elicit unsafe behaviors. In this work, we introduce bijection learning, a pow…