RoboPAD: Post-Training Adaptation of Robot Foundation Models

RoboPAD examines adapting robot foundation models after pre-training. Researchers discuss specialization for new environments, people, objects, tasks and embodiments, including correcting failures and evaluating improvements without repeating the entire original training process. Session: 08:30–18:15 (Europe/Paris). A paid NeurIPS virtual pass includes workshop livestreams; on-site access follows the host-location registration rules.