# Vision-Language Model

[2026-08-26] V-Rubrics: Visual Faithfulness via Rubric-Based Reinforcement Learning

V-Rubrics 怎样把视觉问答拆成 VF、RC、IF criteria，再做 component-wise prefix credit；包含真实 AI2D 样本、judge 输入、reward 重算、结果与公开…