Large Vision-Language Models (VLMs) excel at understanding and generating video descriptions but their high memory, computation, and deployment demands hinder practical use particularly for blind and low-vision (BLV) users who depend on detailed, context-aware descriptions. To study the effect of model size on accessibility-focused description quality, we evaluate SmolVLM2 variants with 500M and 2.2B parameters across two diverse datasets: AVCaps (outdoor), and Charades (indoor). In this work, we introduce two novel evaluation frameworks specifically designed for BLV accessibility assessment: the Multi-Context BLV Framework evaluating spatial orientation, social interaction, action events, and ambience contexts; and the Navigational Assistance Framework focusing on mobility-critical information. Additionally, we conduct a systematic evaluation of four different prompt design strategies and deploy both models on a smartphone, evaluating FP32 and INT8 precision variants to assess real-world performance constraints on resource-limited mobile devices.
@article{arxiv.2511.10615,
title = {Towards Blind and Low-Vision Accessibility of Lightweight VLMs and Custom LLM-Evals},
author = {Shruti Singh Baghel and Yash Pratap Singh Rathore and Sushovan Jena and Anurag Pradhan and Amit Shukla and Arnav Bhavsar and Pawan Goyal},
journal= {arXiv preprint arXiv:2511.10615},
year = {2025}
}