作者位次 #2/9ACL 2026Poster· Natural Language Processing
Learning What Matters: Dynamic Dimension Selection and Aggregation for Interpretable Vision-Language Reward Modeling
Qiyuan Chen · Hongsen Huang · Jiahe Chen · Qian Shao · Jintai Chen · Hongxia Xu · Renjie Hua · Ren Chuan · JIAN Wu
摘要
Vision-language reward modeling faces a dilemma: generative approaches are interpretable but slow, while discriminative ones are efficient but act as opaque “black boxes.” To bridge this gap, we propose VL-MDR (Vision-Language Multi-Dimensional Reward), a framework that dynamically decomposes eva...