作者位次 #3/3ICLR 2026Poster· General Machine Learning / Transfer, Multitask and Meta-learning
TokMem: One-Token Procedural Memory for Large Language Models
Zijun Wu · Yongchang Hao · Lili Mou
检索与知识OpenReview
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。
Zijun Wu · Yongchang Hao · Lili Mou
Yongchang Hao · Lili Mou
Yihong Dong · Xue Jiang · Yongding Tao · Huanyu Liu · Kechi Zhang · Lili Mou · Rongyu Cao · YINGWEI MA · Jue Chen · Binhua Li · Zhi Jin · Fei Huang · Yongbin Li · Ge Li
Reinforcement Learning with Verifiable Reward (RLVR) has significantly advanced the complex reasoning abilities of Large Language Models (LLMs). However, it struggles to break through the inherent capability boundaries of the base LLM, due to its essentially on-policy strategy coupled with LLM’s...
Yongchang Hao · Jie Hao · Yongsheng Mei · Ze Ye · Junyi Chai · Bin Guo · Benjamin Z. Yao · Chenlei Guo · Lili Mou
Reinforcement learning (RL) has become a cornerstone of the post-training pipeline for large language models (LLMs), enabling capabilities such as complex reasoning and tool use. However, standard RL approaches face significant challenges due to reward sparsity. Moreover, LLMs typically exhibit m...
Yuxing Chen · Guoqing Luo · Zijun Wu · Lili Mou
Large Language Models (LLMs) exhibit social biases, which can lead to harmful stereotypes and unfair outcomes. We propose Multi-Persona Thinking (MPT), a simple inference-time framework that reduces social bias by encouraging reasoning from multiple perspectives. MPT guides the model to consider...
Zheng Fang · Yihong Dong · Lili Mou · Dongming Jin · Zhi Jin · Ge Li
Large Language Models (LLMs) have shown strong capabilities in code generation, but their adherence to fine-grained user intent with multiple constraints remains a significant challenge. Our empirical analysis reveals two key observations: 1) Model performance deteriorates quickly as the number o...