作者位次 #4/6ICLR 2026Poster· Applications / Language, Speech and Dialog
PAMDP: Interact to Persona Alignment via a Partially Observable Markov Decision Process
ZHE YANG · Yi Huang · Si Chen · Xiaoting Wu · Jingyu Yao · Junlan Feng
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。
ZHE YANG · Yi Huang · Si Chen · Xiaoting Wu · Jingyu Yao · Junlan Feng
Xiaoting Wu · Yi Huang · Chunyang Gao · Mengfei Guo · Jingyu Yao · Junlan Feng
Existing user simulators based on prompting to role-play or SFT are generally confined to imitating users’ textual utterances, without adequately considering the multi-faceted cognitive processes that underlie human decision-making during interactions. To facilitate better alignment with real hum...
Chunyang Gao · Yi Huang · Jingyu Yao · Xiaoting Wu · Junlan Feng
Despite the remarkable evolution of Large Language Models (LLMs) from simple assistants to versatile agents, effective personalization remains a significant challenge. Existing approaches often treat user preferences as static or merely time-varying traits, overlooking the dynamic nature of human...
ZHE YANG · Yi Huang · Yaqin Chen · Mengfei Guo · Xiaoting Wu · Junlan Feng
In the realm of domain-specific natural language understanding (NLU) tasks, acquiring high-quality labeled data is often arduous, thereby posing significant challenges for effective model training. Multi-task learning (MTL) addresses these limitations by jointly optimizing multiple tasks within a...