作者位次 #5/6ICLR 2026Poster· Computer Vision / Vision Models & Multimodal
ProxyThinker: Test-Time Guidance through Small Visual Reasoners
Zilin Xiao · Jaywon Koo · Siru Ouyang · Jefferson Hernandez · Yu Meng · Vicente Ordonez
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。
Zilin Xiao · Jaywon Koo · Siru Ouyang · Jefferson Hernandez · Yu Meng · Vicente Ordonez
Shangjian Yin · Zhepei Wei · Xinyu Zhu · Wei-Lin Chen · Yu Meng
Traditional reinforcement learning from human feedback (RLHF) for large language models (LLMs) relies on expensive human-annotated datasets, while Reinforcement Learning from AI Feedback (RLAIF) also incurs significant costs, requiring the collection of diverse prompts and corresponding responses...