作者位次 #5/5ICML 2026Poster· Reinforcement Learning / Batch/Offline
Q-Flow: Stable and Expressive Reinforcement Learning with Flow-based Policy
JaeHyeok Doo · Byeongguk Jeon · Seonghyeon Ye · Kimin Lee · Minjoon Seo
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。
JaeHyeok Doo · Byeongguk Jeon · Seonghyeon Ye · Kimin Lee · Minjoon Seo
Jiyeon Kim · Sungik Choi · Yongrae Jo · Moontae Lee · Minjoon Seo
Jiyeon Kim · Hyunji Lee · Dylan Zhou · Sue Hyun Park · Seunghyun Yoon · Trung Bui · Franck Dernoncourt · Sungmin Cha · Minjoon Seo
LLMs operating in dynamic real-world contexts often encounter knowledge that evolves continuously or emerges incrementally. To remain accurate and effective, models must adapt to newly arriving information on the fly. We introduce Online Adaptation to Continual Knowledge Streams(OAKS) to evaluate...