New benchmark shows frontier VLMs still can't read Braille despite 43M blind users
prajdabre · x · 2026-11-02
Researcher prajdabre introduced "Learning to Read Braille: Benchmarking and Improving Braille Recognition Capabilities of VLMs." Context: 43 million people worldwide are blind (about 8 million in India alone), with Braille literacy estimated at only 1%. Despite frontier models setting records in math, coding and science, they still can't read Braille well — a tactile script that poses a unique challenge for vision models. The work provides a benchmark and methods to improve VLM Braille recognition, benefiting families, teachers and transcribers around Braille readers.
More from Research
- Xiaomi MiMo's CodeSpecWeave trains coding agents on interdependent specs for long-horizon coding — XiaomiMiMo · 2026-11-02
- Hunting for the most concrete "curing cancer with AI" roadmap of 2025 — iskander · 2026-11-02
- New theory paper proves linear decay is the unique minimax-optimal stepsize schedule for SGD — konstmish · 2026-11-02
- Karpathy's nanochat: the best ChatGPT $100 can buy, near 60k GitHub stars — karpathy · 2026-11-02
- After reading 46 resources on agent evals, one author explains why her 95% score was misleading — blaizedsouza · 2026-11-02
- Meta & MIT paper: looping transformer layers beats adding depth at fixed size — rohanpaul_ai · 2026-11-02