# SymbolSight: Minimizing Inter-Symbol Interference for Reading with Prosthetic Vision

arXiv: https://arxiv.org/abs/2601.17326 · HTML: https://mlsanity.com/paper/2601.17326/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 29 references that are in the map.
- First posted on arXiv 24 Jan 2026.

## Builds on (most cited first, 6 of 6)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Human-in-the-Loop Optimization for Deep Stimulus Encoding in Visual Prostheses](https://mlsanity.com/paper/2306.13104/) (2023)
- [Deep Learning--Based Scene Simplification for Bionic Vision](https://mlsanity.com/paper/2102.00297/) (2021)
- [Predicting the Temporal Dynamics of Prosthetic Vision](https://mlsanity.com/paper/2404.14591/) (2024)
- [Simulated prosthetic vision confirms checkerboard as an effective raster pattern for epiretinal implants](https://mlsanity.com/paper/2501.02084/) (2025)

## Abstract (arXiv)

Retinal prostheses restore limited visual perception, but low spatial resolution and temporal persistence make reading difficult. In sequential letter presentation, the afterimage of one symbol can interfere with perception of the next, leading to systematic recognition errors. Rather than relying on future hardware improvements, we investigate whether optimizing the visual symbols themselves can mitigate this temporal interference. We present SymbolSight, a computational framework that selects symbol-to-letter mappings to minimize confusion among frequently adjacent letters. Using simulated prosthetic vision (SPV) and a neural proxy observer, we estimate pairwise symbol confusability and optimize assignments using language-specific bigram statistics. Across simulations in Arabic, Bulgarian, and English, the resulting heterogeneous symbol sets reduced predicted confusion by a median factor of 22 relative to native alphabets. These results suggest that standard typography is poorly matched to serial, low-bandwidth prosthetic vision and demonstrate how computational modeling can narrow the design space of visual encodings, identifying high-potential candidates for future psychophysical and clinical evaluation rather than predicting present-day clinical reading performance directly.