Summary of Viassist: Adapting Multi-modal Large Language Models For Users with Visual Impairments, by Bufang Yang et al.
VIAssist: Adapting Multi-modal Large Language Models for Users with Visual Impairments
by Bufang Yang, Lixing He, Kaiwei Liu, Zhenyu Yan
First submitted to arxiv on: 3 Apr 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed VIAssist system leverages multi-modal large language models (MLLMs) to help visually impaired individuals understand visual information and answer visual-based questions. The system identifies and corrects undesired images, providing detailed actions for users with partial or total visual impairments. Experimental results demonstrate the effectiveness of VIAssist, achieving higher BERTScore and ROUGE scores compared to a baseline model (+0.21 and +0.31, respectively). |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary VIAssist is a system that helps people who are blind or have low vision understand pictures and answer questions about what they see. It uses special computer models to look at images and fix any problems with them. This makes it easier for people with visual impairments to use these models to get the information they need. |
Keywords
* Artificial intelligence * Multi modal * Rouge
