Open access
2026
Severity Matters: Risk-Calibrated Reinforcement Fine-Tuning for Clinically Aligned Medical Vision–Language Models
R risk-Calibrated Reinforcement Fine-Tuning addresses this mismatch by making severity an explicit signal in reinforcement learning rather than an after-the-fact evaluation stratum, indicating that the method favors positive association between utility and case severity rather than simple reward amplification.
Yu Su, Peng Wang
· IEEE Access · 0 citations