一作ICLR 2026Poster· Reinforcement Learning / Planning
ReCAPA: Hierarchical Predictive Correction to Mitigate Cascading Failures
Xiyin Zeng · Yuyu Sun · Haoyang Li · Shouqiang Liu · Hao Wang
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。
Xiyin Zeng · Yuyu Sun · Haoyang Li · Shouqiang Liu · Hao Wang
Visual Question Answering (VQA) requires models to identify the correct answer options based on both visual and textual evidence. Recent Mixture-of-Experts (MoE) methods improve option reasoning by grouping similar concepts or routing based on examples. However, unstable routing can lead to incon...