Towards Blind and Low-Vision Accessibility of Lightweight VLMs and Custom LLM-Evals
On the map: Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
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.
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.
Builds on
2 of 17 references.
References · 2
Built on by
Citing papers per year: 2026: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2025Are Large Vision-Language Models Ready to Guide Blind and Low-Vision Individuals?
- 2025How Blind and Low-Vision Individuals Prefer Large Vision-Language Model-Generated Scene Descriptions
- 2026Exploring the Use of VLMs for Navigation Assistance for People with Blindness and Low Vision
- 2026How Multimodal Large Language Models Support Access to Visual Information: A Diary Study With Blind and Low Vision People
- 2026VIABench: A Comprehensive Video Benchmark Collected from Blind Individuals for Visual Impairment Assistance
- 2025Evaluating Multimodal Language Models as Visual Assistants for Visually Impaired Users
- 2025Surfacing Variations to Calibrate Perceived Reliability of MLLM-generated Image Descriptions
- 2025Towards Understanding the Use of MLLM-Enabled Applications for Visual Interpretation by Blind and Low Vision People