A Visual Grounding Benchmark for Retinal OCT with Multimodal Large Language Models
Ronald Fecso, José Morano, Botond Fazekas, Paul Widmann-Sedlnitzky, Dorota Himel, Laetita Hinterhuber, Virginia Mares, Andreas Pollreisz, Hrvoje Bogunović
The online reader was unable to display this document directly. This may occur if the repository host is temporarily unreachable, or if security restrictions (CORS) prevent embedded viewing.