Literature Reviews

Reviewed research papers, articles, and publications relevant to digital accessibility.

• AI4XR: AI in Extended Reality for 3D Scene Editing and Accessibility Design

  Junlong Chen (2026) — Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems (CHI EA '26) — Doctoral Consortium

  This CHI '26 Doctoral Consortium paper summarises Junlong Chen's PhD research at the University of Cambridge on integrating AI — specifically large language models (LLMs) and vision-language models (VLMs) — into extended reality (XR) workflows. The r…

  • extended reality
  • virtual reality
  • artificial intelligence
  • large language models
  • vision-language models
  • visual accessibility
  • blind and low vision
  • scene description
  • multimodal interaction
  • doctoral consortium

• "It's trained by non-disabled people": Evaluating How Image Quality Affects Product Captioning with Vision-Language Models

  Kapil Garg, Xinru Tang, Jimin Heo, Dwayne R. Morgan, Darren Gergle, Erik B. Sudderth, Anne Marie Piper (2026) — Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems (CHI '26)

  Garg and colleagues investigate how well Vision-Language Models (VLMs) caption product images taken by blind and low-vision (BLV) people — a high-stakes everyday task that increasingly depends on tools like Be My AI, Microsoft Seeing AI, and general-…

  • blind and low vision
  • vision-language models
  • image captioning
  • product identification
  • hallucinations
  • image quality
  • disability-centric evaluation
  • AI accessibility
  • assistive technology
  • Be My AI
  • Seeing AI

• TouchScribe: Augmenting Non-Visual Hand-Object Interactions with Automated Live Visual Descriptions

  Ruei-Che Chang, Rosiana Natalie, Wenqian Xu, Jovan Zheng Feng Yap, Tiange Luo, Venkatesh Potluri, Anhong Guo (2026) — Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems (CHI '26)

  TouchScribe is a wearable, camera-based assistive system that delivers live, hierarchical visual descriptions of physical objects in response to a blind or low vision (BLV) user's hand-object interactions. The authors argue that existing AI assistant…

  • blind and low vision
  • assistive technology
  • visual descriptions
  • hand-object interactions
  • gestures
  • large language models
  • vision-language models
  • egocentric vision
  • tactile exploration
  • wearable cameras

• iTagPDF: Towards Finally Automating PDF Accessibility

  Peya Mowar, Aaron Steinfeld, Jeffrey P. Bigham (2026) — Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems (CHI '26)

  This CHI 2026 paper from Mowar, Steinfeld, and Bigham (Carnegie Mellon) presents iTagPDF, an automated system for tagging academic research PDFs so they are accessible to screen reader users. The authors argue that PDF accessibility has remained a pe…

  • PDF accessibility
  • tagged PDF
  • PDF remediation
  • automated accessibility
  • document layout analysis
  • LLM
  • vision-language models
  • LaTeX
  • alt text
  • reading order
  • scholarly publishing
  • automated testing

• Making Lecture Videos Accessible for Students who are Blind or have Low Vision through AI-Assisted Navigation and Visual Question Answering

  Katharina Anderer, Karin Müller, Lukas Strobel, Matthias Wölfel, Jan Niehues, Kathrin Gerling (2025) — Proceedings of the 27th International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS 2025)

  This paper presents the design and evaluation of LectureAssistant, an AI-powered prototype that makes lecture videos more accessible for students who are blind or have low vision. The research follows a three-part human-centred design process. First,…

  • blind and low vision
  • lecture accessibility
  • higher education
  • large language models
  • vision-language models
  • AI-assisted accessibility
  • video accessibility
  • screen readers

• Exploring Object Status Recognition for Recipe Progress Tracking in Non-Visual Cooking

  Franklin Mingzhe Li, Kaitlyn Ng, Bin Zhu, Patrick Carrington (2025) — ASSETS 2025: 27th International ACM SIGACCESS Conference on Computers and Accessibility

  This paper presents OSCAR (Object Status Context Awareness for Recipes), a technical pipeline that uses object status recognition—tracking the condition and transformation of ingredients and tools—to support recipe progress tracking for blind and low…

  • blind and low vision
  • cooking accessibility
  • context awareness
  • object recognition
  • computer vision
  • vision-language models
  • assistive technology
  • recipe tracking
  • non-visual interaction