作者位次 #7/10NeurIPS 2026Poster
From Label Priors to Task Evidence: Long-Video Frame Selection via Bayesian GRPO
Shuochen Chang · Bingjie Gao · Qingyang Liu · Qianli Ma · Yibo Miao · Haonan Zhao · Zhaohe Liao · Xiaofeng Zhang · Jiangtong Li · Li Niu
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。
Shuochen Chang · Bingjie Gao · Qingyang Liu · Qianli Ma · Yibo Miao · Haonan Zhao · Zhaohe Liao · Xiaofeng Zhang · Jiangtong Li · Li Niu
Shuochen Chang · Tong Bai · Xiaofeng Zhang · Qianli Ma · Qingyang Liu · Zhaohe Liao · Yibo Miao · Li Niu
Latent reasoning enables Large Language Models (LLMs) to perform multi-step inference within continuous hidden states, offering efficiency gains over explicit Chain-of-Thought (CoT). However, the opacity of these continuous thought vectors hinders their reliability and controllability. This paper...