🩺 Medical LLM

📷 CVPR2026 · 1 paper notes

📌 Same area in other venues: 🔬 ICLR2026 (20) · 💬 ACL2026 (47) · 🧪 ICML2026 (4) · 🤖 AAAI2026 (12) · 🧠 NeurIPS2025 (17) · 🧪 ICML2025 (4)

Towards Efficient Medical Reasoning with Minimal Fine-Tuning Data

This paper proposes the Difficulty-Influence Quadrant (DIQ) data selection strategy, which jointly considers sample difficulty and gradient influence. This approach allows a VLM's language backbone to match full SFT performance using only 1% of curated data and exceed full-dataset training with 10% of the data.