作者位次 #3/6ICLR 2026Poster· Theory / Domain Adaptation and Transfer Learning
IMSE: Intrinsic Mixture of Spectral Experts Fine-tuning for Test-Time Adaptation
Sunghyun Baek · Jaemyung Yu · Seunghee Koh · Minsu Kim · Hyeonseong Jeon · Junmo Kim
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。
Sunghyun Baek · Jaemyung Yu · Seunghee Koh · Minsu Kim · Hyeonseong Jeon · Junmo Kim
Seunghee Koh · Sunghyun Baek · Youngdong Kim · Junmo Kim
Unlearning in large language models (LLMs) has emerged as a promising safeguard against adversarial behaviors. When the forgetting loss is applied uniformly without considering token-level semantic importance, model utility can be unnecessarily degraded. Recent studies have explored token-wise lo...