一作ECCV 2026Poster
EpiBench: Benchmarking Multi-turn Research Workflows for Multimodal Agents
Xuan Dong · Huanyang Zheng · Tianhao Niu · Zhe Han · Pengzhan Li · Bofei Liu · Zhengyang Liu · Guancheng Li · Qingfu Zhu · Wanxiang Che
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Xuan Dong · Huanyang Zheng · Tianhao Niu · Zhe Han · Pengzhan Li · Bofei Liu · Zhengyang Liu · Guancheng Li · Qingfu Zhu · Wanxiang Che
Xuan Dong · Zhe Han · Tianhao Niu · Qingfu Zhu · Wanxiang Che
Vision-Language-Action (VLA) models have shown strong performance in language-conditioned robotic manipulation, yet their robustness to linguistic variation remains poorly understood. In this work, We present the first systematic multilingual evaluation of VLA models by translating the LIBERO ben...