類似資料

• FedPOB: Sample-Efficient Federated Prompt Optimization via Bandits
  著者:: Lu, Pingchen, 等
  出版事項: (2025)
• T-POP: Test-Time Personalization with Online Preference Feedback
  著者:: Qu, Zikun, 等
  出版事項: (2025)
• ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment
  著者:: Lin, Xiaoqiang, 等
  出版事項: (2025)
• Policy Improvement Reinforcement Learning
  著者:: Wang, Huaiyang, 等
  出版事項: (2026)
• Refining Adaptive Zeroth-Order Optimization at Ease
  著者:: Shu, Yao, 等
  出版事項: (2025)