notesum.ai

Published at November 26

VLRewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models

cs.CV

cs.CL

Released Date: November 26, 2024

Authors: Lei Li¹, Yuancheng Wei², Zhihui Xie¹, Xuqing Yang³, Yifan Song⁴, Peiyi Wang⁴, Chenxin An¹, Tianyu Liu⁴, Sujian Li⁴, Bill Yuchen Lin⁵, Lingpeng Kong¹, Qi Liu⁴

Aff.: ¹HKU; ²SCUT; ³SJTU; ⁴PKU; ⁵UW

Arxiv: http://arxiv.org/abs/2411.17451v1