IEEE

Constraint-Aware Zero-Shot Vision-Language Navigation in Continuous Environments

Abstract: We address the task of Vision-Language Navigation in Continuous Environments (VLN-CE) under the zero-shot setting. Zero-shot VLN-CE is particularly challenging due to the absence of expert ...
IEEE

Beyond General Prompts: Automated Prompt Refinement Using Contrastive Class Alignment Scores for Disambiguating Objects in Vision-Language Models

Abstract: Vision-language models (VLMs) offer flexible object detection through natural language prompts but suffer from performance variability depending on prompt phrasing. In this paper, we ...