Can captions teach medical VLMs to see artifacts? (SPIE) Adapters (Qwen3-VL-8B, MedGemma-4B) and evaluation from our SPIE study on caption fine-tuning for medical figure captioning. akmaier/qwen3vl-8b-figcaption-lora Image-Text-to-Text • Updated Aug 3 akmaier/medgemma-4b-figcaption-lora Image-Text-to-Text • Updated Aug 3
Can captions teach medical VLMs to see artifacts? (SPIE) Adapters (Qwen3-VL-8B, MedGemma-4B) and evaluation from our SPIE study on caption fine-tuning for medical figure captioning. akmaier/qwen3vl-8b-figcaption-lora Image-Text-to-Text • Updated Aug 3 akmaier/medgemma-4b-figcaption-lora Image-Text-to-Text • Updated Aug 3
