FOUNDATION OPHTHALMIC CROSS-DATASET UNDERSTANDING UNDER SHIFT
A clearer view of
retinal model reliability.
Explore vision encoders, dual encoder vision-language models and multimodal LLMs across performance, calibration, fairness and robustness.
Loading benchmark results…
THE RESEARCH
Beyond a single leaderboard.
FOCUS: Benchmarking Retinal Model Generalization from Foundation Vision Encoders to Multimodal LLMs.
Paper & citation ↗Accepted at NeurIPS 2026 · Evaluations & Datasets Track