一作NeurIPS 2026Poster· Computer Vision / Vision Models & Multimodal
Video Models Can Reason with Verifiable Rewards
Tinghui Zhu · Sheng Zhang · James Yipeng Huang · Selena Song · Xiaofei Wen · Yuankai Li · Hoifung Poon · Muhao Chen
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。
Tinghui Zhu · Sheng Zhang · James Yipeng Huang · Selena Song · Xiaofei Wen · Yuankai Li · Hoifung Poon · Muhao Chen
Sirui Xia · Aili Chen · Xintao Wang · Tinghui Zhu · Yikai Zhang · Jiangjie Chen · Yanghua Xiao
Recent advances in Large Language Models (LLMs) have demonstrated strong capabilities in tasks such as code generation and mathematical reasoning. However, their potential to internalize structured spatial knowledge remains underexplored. This study investigates whether LLMs, grounded in locally...