Kun Yang

kun_photo.png

Hello! I’m Kun Yang, a Senior Data Scientist at Juniper Networks, working on auto radio resource allocation for smart WIFI systems. I recently completed my Ph.D. at the University of Virginia (UVA), where I worked under the guidance of Professor Cong Shen. My research primarily focuses on reinforcement learning (RL) and its innovative applications in optimizing wireless networks. I’m currently delving into the use of offline RL to tackle complex challenges in this field. Additionally, I have a keen interest in Federated Learning and the broader spectrum of General RL frameworks. Our recent venture involves exploring prompt engineering for large language models (LLMs). I welcome collaboration and discussions with those who share these research interests.

Apart from my academic endeavors, I’m an avid basketball player and video game enthusiast. I firmly believe that these hobbies not only foster a healthier lifestyle but also positively influence my research journey.

For a deeper dive into my research work, publications, and academic path, I invite you to visit my website.

news

Sep 25, 2024 I’m thrilled to share that two of our papers have been accepted to NeurIPS 2024, with online version and videos coming soon. Looking forward to see you in Vancouver!
Sep 18, 2024 My accepted paper Average Reward Reinforcement Learning for Wireless Radio Resource Management to IEEE Asilomar 2024, together with Prof. Cong Shen (UVA) and Prof. Jing Yang (PSU), have joined the finalist of the Best student paper award.
Jun 15, 2024 Our paper, Harnessing the Power of Federated Learning in Federated Contextual Bandits!, co-authored with Chengshuai Shi (UVA), Ruida Zhou (UCLA), and Cong Shen (UVA), has been accepted by Transactions on Machine Learning Research (TMLR).
May 17, 2024 Our work on utilizing offline RL for wireless communication has been accepted for publication in IEEE. Transaction on Wireless Communication. Check the manuscipt here!
Feb 15, 2024 Suffering with the budget constraint while selecting the best prompt for your LLM? Check out recent work: Best Arm Identification for Prompt Learning under a Limited Budget!

selected publications

2024

  1. Efficient Prompt Optimization Through the Lens of Best Arm Identification
    Chengshuai Shi*, Kun Yang*, Zihan Chen, and 3 more authors
    Advances in neural information processing systems, 2024
  2. Transformers as Game Players: Provable In-context Game-playing Capabilities of Pre-trained Models
    Chengshuai Shi, Kun Yang, Jing Yang, and 1 more author
    Advances in neural information processing systems, 2024

2022

  1. On the Convergence of Hybrid Server-Clients Collaborative Training
    Kun Yang, Shengbo Chen, and Cong Shen
    IEEE Journal on Selected Areas in Communications, 2022