Sören Pirk

COOL: Curiosity-Driven Object Ownership Learning for Personalized Robotic Assistance

Robots are increasingly expected to provide personalized services in everyday environments. To do so, they must ground natural-language commands such as"Where is my backpack?"or"Find my bottle"and execute them by reasoning about object instances, people, locations, and ownership. This is challenging because ownership i...

Evaluating Early Multimodal Fusion in Discrete Latent World Models for Robot Navigation

Option-Aware Retrieval and Task-Specific VLM Adaptation for Medical VQA

This submission to the MedReason 2026 challenge is described, covering multiple-choice (MCQ) and open-ended (OE) medical visual question answering (VQA) under fully offline, containerized inference, and it is found that MCQ retrieval must compare answer \emph{semantics} rather than answer labels.

Hydra: A Navigation World Action Model with Discrete Latent Planning and Continuous Flow-Matching Execution

Hydra, a discrete World Action Model that tackles this by establishing a unified latent manifold over visual states, physical poses, and control actions, outperforms state-of-the-art navigation world models in goal-directed planning, while matching or exceeding the closed-loop execution capabilities of leading reactive...