Papers with blind and low-vision users
OpenGlass: A Sensing-Computing Split Architecture for Local MLLM-Driven Real-Time Visual Assistance (2026.acl-demo)
Copied to clipboard
| Challenge: | OpenGlass is an open-source, privacy-oriented, local-first system for low-latency multimodal visual assistance . cloud MLLM assistants offer strong visual understanding but often require uploading first-person visual data . |
| Approach: | They propose an open-source system for low-latency multimodal visual assistance . they use an ESP32-based glasses-side unit to capture visual context . |
| Outcome: | The proposed system captures visual context while a nearby device performs local MLLM inference and speech output. |
Believing without Seeing: Quality Scores for Contextualizing Vision-Language Model Explanations (2026.acl-long)
Copied to clipboard
| Challenge: | Prior work has found that explanations can easily convince users that inaccurate VLM predictions are correct. |
| Approach: | They propose to evaluate two complementary qualities of VLM-generated explanations via two quality scoring functions to improve their accuracy. |
| Outcome: | The proposed explanations improve accuracy on the A-OKVQA, VizWiz, and MMMU-Pro tasks by 11.1%, including a 15.4% reduction in falsely believing incorrect predictions. |