Original Summary

Heyo!<p>I&#x27;m Adit, an undergrad in Finland. This is a preview of a side project I worked on last weekend. Essentially, Dragonfly is a LoRA fine-tune of Qwen3-VL with typed output heads that answers many questions about an image in one pass, with a probability for every answer. Unlike a VLM that generates an answer to each question, Dragonfly reads the image once and scores every question in the same pass. Questions can&#x27;t see each other, so each answer is the same as asking it alone, in any order.<p>Instead of text outputs, Dragonfly answers with calibrated probabilities for the options you give it in order to answer the question. You can ask Dragonfly multiple choice, yes&#x2F;no, or scale-based questions.<p>As you might have guessed already, I got the idea from Jev and thought it would be fun to train a small model that can do the same thing for images. There wasn&#x27;t a dataset for questions specifically, so I compiled a couple open datasets to form around half of our training data and then distilled Qwen to generate ~300k questions that I could verify against the human annotated data.<p>Try it out @ <a href="https:&#x2F;&#x2F;adit.run&#x2F;dragonfly" rel="nofollow">https:&#x2F;&#x2F;adit.run&#x2F;dragonfly</a> and lmk what you think :)

  • 情报分类：综合情报
  • 分类依据：内容未命中明确的垂直分类规则，归入综合情报
  • 信息来源：Hacker News 新项目
  • 发布时间：2026/10/13 19:16:00