MAIS, Institute of Automation, Chinese Academy of Sciences
中国科学院自动化研究所 多模态人工智能系统全国重点实验室👨🔬 About Me
I am Kun Chen, a two-year PhD student at the State Key Laboratory of Multimodal Artificial Intelligence Systems(MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), majoring in Computer Application Technology. Before that, I received my B.Eng. degree in Automation from University of Electronic Science and Technology of China (UESTC) in 2024.
🌱 Interests
My research interests focus on Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs), including training, alignment (RLHF/RLVR), agentic systems, and long-context extension. I thrive on following cutting-edge AI research, actively contributing to open-source communities.
👨🔬 关于我
我是陈坤， 中国科学院自动化研究所 多模态人工智能系统全国重点实验室（MAIS） 二年级博士研究生，专业为计算机应用技术。 此前，于2024年获得 电子科技大学 自动化专业工学学士学位。
🌱 研究兴趣
我的研究方向聚焦于大语言模型（LLMs）和多模态大语言模型（MLLMs）， 涵盖模型训练、对齐（RLHF/RLVR）、智能体系统以及长上下文扩展等方向。 我热衷于追踪前沿AI研究，积极参与开源社区贡献。
Education教育经历
-
Institute of Automation, Chinese Academy of SciencesComputer Application Technology
Ph.D. Student, Supervised by Wenji MaoSep. 2024 - present -
University of Electronic Science and Technology of ChinaAutomation (GPA 3.94)
B.Eng. StudentSep. 2020 - Jun. 2024
-
中国科学院自动化研究所计算机应用技术
博士研究生，导师：毛文吉2024年9月 - 至今 -
电子科技大学自动化（GPA 3.94）
工学学士2020年9月 - 2024年6月
Experience工作经历
-
MeituanAlgorithm Research InternAug. 2025 - Feb. 2026 -
Wenge TechAlgorithm Engineer, AI Research InstituteJun. 2024 - Jun. 2025
-
美团算法研究实习生2025年8月 - 2026年2月
-
中科闻歌算法工程师，AI研究院2024年6月 - 2025年6月
Honors & Awards荣誉奖励
-
Outstanding Student of UESTC (Only 10 undergraduate students)2023
-
National First Prize, 18th Challenge Cup National College Students' Extracurricular Academic Science and Technology Works Contest2023
-
National First Prize, 18th National University Students Smart Car Race2023
-
Meritorious Winner, Mathematical Contest in Modeling2023
-
Multiple National Scholarships & SZSE Scholarships2020 - 2025
-
电子科技大学成电杰出学生（全校仅10名本科生）2023
-
第十八届"挑战杯"全国大学生课外学术科技作品竞赛 全国一等奖2023
-
第十八届全国大学生智能车竞赛 全国一等奖2023
-
美国大学生数学建模竞赛 Meritorious Winner2023
-
多次获得国家奖学金及深交所奖学金2020 - 2025
News最新动态
Selected Publications精选论文 (view all)(查看全部)
APEX-Searcher: Augmenting LLMs' Search Capabilities through Agentic Planning and Execution
Kun Chen, Qingchao Kong#, Feifei Zhao, Wenji Mao
ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) 2026 Under Review
We propose APEX-Searcher, a framework that augments LLMs' search capabilities through agentic planning and execution for improved information retrieval.我们提出了APEX-Searcher，一个通过智能体规划与执行来增强大语言模型搜索能力的框架，以改善信息检索效果。
APEX-Searcher: Augmenting LLMs' Search Capabilities through Agentic Planning and Execution
Kun Chen, Qingchao Kong#, Feifei Zhao, Wenji Mao
ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) 2026 Under Review
We propose APEX-Searcher, a framework that augments LLMs' search capabilities through agentic planning and execution for improved information retrieval.我们提出了APEX-Searcher，一个通过智能体规划与执行来增强大语言模型搜索能力的框架，以改善信息检索效果。
Flexible Entropy Control in RLVR with Gradient-Preserving Perspective
Kun Chen, Peng Shi#, Fanfan Liu, Haibo Qiu, Zhixiong Zeng, Siqi Yang, Wenji Mao#
International Conference on Machine Learning (ICML) 2026 Under Review
From the perspective of gradient preservation, we propose an entropy increase and decrease regulation mechanism, as well as three strategies for entropy control in the training of Reinforcement Learning with Verifiable Rewards (RLVR).我们从梯度保持的视角出发，提出了一种熵增熵减的调节机制，并提出三种在可验证奖励强化学习（RLVR）训练中控制熵的策略。
Flexible Entropy Control in RLVR with Gradient-Preserving Perspective
Kun Chen, Peng Shi#, Fanfan Liu, Haibo Qiu, Zhixiong Zeng, Siqi Yang, Wenji Mao#
International Conference on Machine Learning (ICML) 2026 Under Review
From the perspective of gradient preservation, we propose an entropy increase and decrease regulation mechanism, as well as three strategies for entropy control in the training of Reinforcement Learning with Verifiable Rewards (RLVR).我们从梯度保持的视角出发，提出了一种熵增熵减的调节机制，并提出三种在可验证奖励强化学习（RLVR）训练中控制熵的策略。
SPECS: Decoupling Multimodal Learning via Self-distilled Preference-based Cold Start
Kun Chen*, Peng Shi*, Haibo Qiu, Zhixiong Zeng, Siqi Yang, Wenji Mao#, Lin Ma#
International Conference on Learning Representations (ICLR) 2026 Poster
We propose SPECS, a self-distilled preference-based cold start method that decouples multimodal learning to improve multimodal reasoning capabilities.我们提出了SPECS，一种基于自蒸馏偏好的冷启动方法，通过解耦多模态学习来提升多模态推理能力。
SPECS: Decoupling Multimodal Learning via Self-distilled Preference-based Cold Start
Kun Chen*, Peng Shi*, Haibo Qiu, Zhixiong Zeng, Siqi Yang, Wenji Mao#, Lin Ma#
International Conference on Learning Representations (ICLR) 2026 Poster
We propose SPECS, a self-distilled preference-based cold start method that decouples multimodal learning to improve multimodal reasoning capabilities.我们提出了SPECS，一种基于自蒸馏偏好的冷启动方法，通过解耦多模态学习来提升多模态推理能力。
DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling
Minzheng Wang, Xinghua Zhang, Kun Chen, Nan Xu, Haiyang Yu, Fei Huang, Wenji Mao#, Yongbin Li#
Annual Meeting of the Association for Computational Linguistics (ACL) 2025 Findings
We propose DEMO, a framework that reframes dialogue interaction through fine-grained element modeling for improved dialogue understanding and generation.我们提出了DEMO，一个通过细粒度元素建模来重构对话交互的框架，以提升对话理解与生成能力。
DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling
Minzheng Wang, Xinghua Zhang, Kun Chen, Nan Xu, Haiyang Yu, Fei Huang, Wenji Mao#, Yongbin Li#
Annual Meeting of the Association for Computational Linguistics (ACL) 2025 Findings
We propose DEMO, a framework that reframes dialogue interaction through fine-grained element modeling for improved dialogue understanding and generation.我们提出了DEMO，一个通过细粒度元素建模来重构对话交互的框架，以提升对话理解与生成能力。