{"width":"100%","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fiblog.ridge-i.com%2Fentry%2F2025%2F11%2F26%2F184501\" title=\"Investigating fine-tuning limitations for VLMs with three case studies - Ridge-institute R&amp;D Blog\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","provider_url":"https://hatena.blog","title":"Investigating fine-tuning limitations for VLMs with three case studies","author_url":"https://blog.hatena.ne.jp/rouliiiie/","provider_name":"Hatena Blog","description":"Hello, this is Aur\u00e9lie, working as an Artificial Intelligence Engineer at Ridge-i. Today I would like to share some insights about fine-tuning vision language models (VLMs)! Introduction To fine-tune or not to fine-tune Which modules to keep frozen in a VLM when fine-tuning Internal experiments The \u2026","url":"https://iblog.ridge-i.com/entry/2025/11/26/184501","published":"2025-11-26 18:45:01","author_name":"rouliiiie","categories":[],"blog_url":"https://iblog.ridge-i.com/","height":"190","version":"1.0","blog_title":"Ridge-institute R&D Blog","image_url":"https://cdn-ak.f.st-hatena.com/images/fotolife/r/rouliiiie/20250922/20250922123325.png","type":"rich"}