2026
Regulating Anatomy-Aware Rewards via Trajectory-Integral Feedback for Volumetric Computed Tomography Analysis
ICML 2026poster
The advancement of Medical Vision-Language Models (VLMs) for 3D Computed Tomography (CT) analysis is hindered by a misalignment between optimization objectives and clinical rigor. Current Reinforcement Learning (RL) paradigms rely on lexical proxy signals that induce ``\textbf{evaluation hallucinati…