collaborators

6 papers

cs.CV2026

Attention is Case-Sensitive

Maximilian Dillitzer, Tin Stribor Sohn, Jason J. Corso +1

In human visual perception, uppercase lettering serves as a natural salience cue that captures attention within lowercase text. In this paper, we present a systematic empirical cha…

cs.CV2026

Understanding Cross-Rig Generalization in Automotive Perception: a Multi-Rig Benchmark and Rig Variation Metrics

Tim Alexander Bader, Tim Dieter Eberhardt, Maximilian Dillitzer +1

Camera-based perception systems for autonomous driving are typically developed and evaluated using fixed sensor rigs, while real-world vehicle fleets exhibit substantial variation…

cs.RO2025

Embodied4C: Measuring What Matters for Embodied Vision-Language Navigation

Tin Stribor Sohn, Maximilian Dillitzer, Jason J. Corso +1

Vision-language navigation requires agents to reason and act under constraints of embodiment. While vision-language models (VLMs) demonstrate strong generalization, current benchma…

cs.CV2025

SNOW: Spatio-Temporal Scene Understanding with World Knowledge for Open-World Embodied Reasoning

Tin Stribor Sohn, Maximilian Dillitzer, Jason J. Corso +1

Autonomous robotic systems require spatio-temporal understanding of dynamic environments to ensure reliable navigation and interaction. While Vision-Language Models (VLMs) provide…

cs.CV2025

R4: Retrieval-Augmented Reasoning for Vision-Language Models in 4D Spatio-Temporal Space

Tin Stribor Sohn, Maximilian Dillitzer, Jason J. Corso +1

Humans perceive and reason about their surroundings in four dimensions by building persistent, structured internal representations that encode semantic meaning, spatial layout, and…

cs.CV2025

A Framework for a Capability-driven Evaluation of Scenario Understanding for Multimodal Large Language Models in Autonomous Driving

Tin Stribor Sohn, Philipp Reis, Maximilian Dillitzer +3

Multimodal large language models (MLLMs) hold the potential to enhance autonomous driving by combining domain-independent world knowledge with context-specific language guidance. T…