作者位次 #5/6CVPR 2026Poster· Computer Vision & Pattern Recognition
GDFA: Geometry-Driven Federated Unlearning with Directional Task Vector Alignment
Xiuting Weng · Ruizhi Pu · Yuanhang Yao · Kun Yue · Zhiwen Tang · Lixing Yu
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。
Xiuting Weng · Ruizhi Pu · Yuanhang Yao · Kun Yue · Zhiwen Tang · Lixing Yu
Wei Zhu · Jian Zhang · Lixing Yu · Kun Yue · Zhiwen Tang
Large Language Models (LLMs) achieve strong performance through extended inference-time deliberation, yet how their reasoning failures arise remains poorly understood. By analyzing model-generated reasoning trajectories, we find that errors are not uniformly distributed but often originate from a...