作者位次 #2/6ICLR 2026Poster· Deep Learning / Generative Models and Autoencoders
Retrieval-of-Thought: Efficient Reasoning via Reusing Thoughts
Ammar Ahmed · Azal Ahmad Khan · Ayaan Ahmad · Sheng Di · Zirui Liu · Ali Anwar
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。
Ammar Ahmed · Azal Ahmad Khan · Ayaan Ahmad · Sheng Di · Zirui Liu · Ali Anwar
Anas Mohamed · Azal Ahmad Khan · Xinran Wang · Ahmad Faraz Khan · Shuwen Ge · Saman Bahzad Khan · Ayaan Ahmad · Ali Anwar
Generative AI can now synthesize strikingly realistic images from text, yet output quality remains highly sensitive to how prompts are phrased. Direct Preference Optimization (DPO) offers a lightweight, off-policy alternative to RL for automatic prompt engineering, but its token-level regularizat...