{"paper":{"title":"An integrated language-vision foundation model for conversational diagnostics and triaging in primary eye care","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Can Can Xue, Charumathi Sabanayagam, Ching-Yu Cheng, Ecosse Lamoureux, Jiangnan He, Jie Xu, Jost B. Jonas, Kai Yu, Lavanya Raghavan, Lee Ching Linette Phang, Ming-Chih Ho, Preeti Gupta, Qingsheng Peng, Quan V. Hoang, Rachel Shujuan Chong, Rick Siow Mong Goh, Sahil Thakur, Seang Mei Saw, Songhomitra Panda-Jonas, Tien Yin Wong, Vinay Nangia, Wei-Chi Wu, Xiaofeng Lei, Xinxing Xu, Yang Bai, Yang Zhou, Ya Xing Wang, Yih Chung Tham, Yong Liu, Zann Lee, Zhi Da Soh","submitted_at":"2025-05-13T10:13:26Z","abstract_excerpt":"Current deep learning models are mostly task specific and lack a user-friendly interface to operate. We present Meta-EyeFM, a multi-function foundation model that integrates a large language model (LLM) with vision foundation models (VFMs) for ocular disease assessment. Meta-EyeFM leverages a routing mechanism to enable accurate task-specific analysis based on text queries. Using Low Rank Adaptation, we fine-tuned our VFMs to detect ocular and systemic diseases, differentiate ocular disease severity, and identify common ocular signs. The model achieved 100% accuracy in routing fundus images to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08414","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.08414/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}