Adapters (Qwen3-VL-8B, MedGemma-4B) and evaluation from our SPIE study on caption fine-tuning for medical figure captioning.
Andreas Maier
akmaier
·
AI & ML interests
None yet
Recent Activity
updated a model 4 days ago
akmaier/medgemma-4b-figcaption-lora updated a model 4 days ago
akmaier/qwen3vl-8b-figcaption-lora updated a collection 4 days ago
Can captions teach medical VLMs to see artifacts? (SPIE)Organizations
