2 papers
cs.LG2026
VERPO: Verified Evidence Regularized Policy Optimization
Haijiang Li, Chengyu Lv, Yi Zhang +12
Verifiable rewards improve language models through reliable task-level feedback, but methods based on Group Relative Policy Optimization (GRPO) apply a sequence-level advantage uni…
cs.CV2025
MedGEN-Bench: A Contextually Entangled Benchmark for Open-ended Multimodal Medical Generation
Junjie Yang, Yuhao Yan, Gang Wu +12
Medical vision-language models (VLMs) are increasingly expected to support clinical workflows through diagnostic text and relevant medical images. However, current medical visual b…