Researcher — paper.dinq.me

2026 顶会论文

作者位次 #4/6ICLR 2026Poster· Theory / Learning Theory

FutureMind: Equipping Small Language Models with Strategic Thinking-Pattern Priors via Adaptive Knowledge Distillation

Shaoxiong Yang · Junting Li · Mengyuan Zhang · Chao Li · WEI LIU · Jian Luan

强化学习与后训练检索与知识理论与学习动力学OpenReview

作者位次 #3/6ACL 2026Poster· Natural Language Processing

End-to-End Optimization of LLM -Driven Multi-Agent Search Systems via Heterogeneous-Group-Based Reinforcement Learning

Guanzhong Chen · Shaoxiong Yang · Chao Li · WEI LIU · Jian Luan · Zenglin Xu

摘要

Large language models (LLMs) are versatile, yet their deployment in complex real-world settings is limited by static knowledge cutoffs and the difficulty of producing controllable behavior within a single inference. Multi-agent search systems (MASS), which coordinate specialized LLM agents equipp...

检索与知识强化学习与后训练智能体与工具OpenReview 项目页

作者位次 #11/16IROS 2026Poster· Agents and Memory for Robust VLA Manipulation

E³VT: An Effective and Efficient VLA Framework for Embodied Visual Tracking in the Wild

Yuzhe Ji · Peipeng Chen · Xiexing Feng · Peng Zhang · WEI LIU · Ruyi Li · Youji Zhu · Wei Tianyuan · Lun Luo · Datong Bao · Chao Li · Wanqi ZHOU · Yi Liu · Liuqing Yang · Haoang Li · Xinhu Zheng

智能体与工具多模态效率与系统AI-Enabled RoboticsEmbodied Cognitive ScienceDeep Learning for Visual PerceptionOpenReview

Chao Li

获取完整研究档案

联系方式

2026 顶会论文

FutureMind: Equipping Small Language Models with Strategic Thinking-Pattern Priors via Adaptive Knowledge Distillation

End-to-End Optimization of LLM -Driven Multi-Agent Search Systems via Heterogeneous-Group-Based Reinforcement Learning

E³VT: An Effective and Efficient VLA Framework for Embodied Visual Tracking in the Wild

常见合作者