Supports record-keeping and situational awareness at disaster medical sites, working from the conversations and wound images that occur there. The team identified where LFM fell short, prepared data and fine-tuned to close the gap — unusually thorough execution for a hackathon window.
Fine-tuning inside a hackathon window is rare. KOKU AI identified where LFM fell short, prepared data and closed the gap, and that execution is what carried the entry. The subject choice fits the method: in disaster medicine both hands and eyes are occupied, so building records out of the conversation and the wounds already in view has an obvious logic. Measuring a model's weak spots and fixing them, rather than showing the model off, is what a gold award rewards.
Summaries are written by this site. Project pages include demo videos, screenshots and the team's own write-up (videos may autoplay).