AI RESEARCH
Goal2Pixel: Grounding Goals to Pixels for Vision-Language Navigation
arXiv CS.CV
•
ArXi:2606.01621v1 Announce Type: new Vision-language models (VLMs) have become a common foundation for vision-and-language navigation in continuous environments (VLN-CE). Yet most VLM-based methods cast navigation as low-level action prediction, an interface that is ambiguous, tied to short-horizon motion primitives, and inefficient due to repeated VLM querying. We propose Goal2Pixel, a pure pixel-based paradigm that reformulates VLN-CE as navigable pixel grounding.