作者位次 #2/9ECCV 2026Poster
StreamSpatial: A Benchmark and Framework for Streaming 3D Visual-Spatial Reasoning
Junlin Xie · Keyang Zhong · Quanlong Zheng · Ruifei Zhang · Kuo Wang · Yanhao Zhang · Haonan Lu · Xiang Wan · Guanbin Li
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。
Junlin Xie · Keyang Zhong · Quanlong Zheng · Ruifei Zhang · Kuo Wang · Yanhao Zhang · Haonan Lu · Xiang Wan · Guanbin Li
Keyang Zhong · Junlin Xie · Hefeng Wu · Haofeng Li · Guanbin Li
Vision-language models (VLMs) have shown impressive capabilities in perceptual tasks, yet they degrade in complex multi-hop reasoning under multi-player game settings with imperfect and deceptive information. In this paper, we pick up a representative multi-player task, Murder Mystery Games, whic...