# Towards Blind and Low-Vision Accessibility of Lightweight VLMs and Custom LLM-Evals

arXiv: https://arxiv.org/abs/2511.10615 · HTML: https://mlsanity.com/paper/2511.10615/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 2 of its 17 references that are in the map.
- First posted on arXiv 13 Nov 2025.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 2 of 2)

- [Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding](https://mlsanity.com/paper/1604.01753/) (2016)
- [VideoA11y: Method and Dataset for Accessible Video Description](https://mlsanity.com/paper/2502.20480/) (2025)

## Built on by (most cited first, 2 of 2)

- [Toward Scalable Audio Description Quality Control: A Workflow for Evaluating Human and VLM Raters](https://mlsanity.com/paper/2602.01390/) (2026)
- [Small yet Assistive: Spatially-Aware Post-Training for Low Vision](https://mlsanity.com/paper/2609.28757/) (2026)

## Abstract (arXiv)

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.