Duo Wu
(吴铎)
ABOUT
Hi! I am currently a second-year Ph.D. student at Tsinghua University, advised by Prof. Zhi Wang. Before that, I obtained my M.Phil. degree in Computer and Information Engineering from The Chinese University of Hong Kong, Shenzhen in 2024, advised by Prof. Fangxin Wang, and B.Eng. degree in Computer Science and Technology from Jinan University in 2022, advised by Prof. Lin Cui.
I am fortunate to lead "Decision LM", a small but vibrant research team made up of young, enthusiastic, and deeply committed people. Working alongside them is both a joy and an honor.
From 2025/01 to 2025/10, I was also fortunate to join the Network Transmission Research Group, ByteDance, Shenzhen as a research intern, where I worked with Dr. Wei Zhang to position Decision LM in large-scale online network controls.
RECENT NEWS
-
[2025/09] New! Our first work CoBel-World on LLM multi-agent systems is available now! It introduces belief modeling for LLMs to reason like human collaborators!
-
[2025/06] New! Our paper CATP-LLM was accepted by ICCV 2025.
-
[2024/12] Our paper on LLM collaborated fine-tuning was accepted by AAAI 2025.
-
[2024/11] I earned the Presidential Outstanding Graduate Student Award at CUHKSZ (only 10 awardee out of 1500+ master and Ph.D. students).
-
[2024/10] Our paper MANSY was accepted by IEEE Transactions on Mobile Computing.
-
[2024/08] Our paper NetLLM was accepted by ACM SIGCOMM 2024.
RESEARCH INTERESTS
I used to work on designing high-performance video streaming systems with cutting-edge machine learning techniques. Embracing the new opportunities and challenges of large language models (LLMs), I am now focused on harnessing the capabilities of LLMs to solve fundamental decision-making and planning problems across various domains, which I call Decision Large Model (Decision LM).
Vision and Mission: Our research seeks to advance LLMs as intelligent decision agents for efficient task optimization and planning. We aim to overcome key capability bottlenecks across the full "perception-planning-action" pipeline, paving the way for next-generation LLM-driven decision-making systems.
Resarch Areas: LLM Domain Adaptation, LLM Planning and Tool Use, Embodied AI and VLA, Multi-Agent Collaboration.
[Recruiting] We are seeking cooperators (Ph.D., master, undergraduate students) to work on Decision LM😊! Please check out our webpage for details. If you are interested in working with us, feel free to contact me or Zhi Wang🤗!
PUBLICATION
Note: Equal contribution is marked by *. Advised students are underlined.
Selected Publications:
-
CATP-LLM: Empowering Large Language Models for Cost-Aware Tool Planning
Accepted by ICCV 2025 [CCF-A] preprint code
Duo Wu*, Jinghe Wang*, Yuan Meng*, Yanning Zhang, Le Sun, Zhi Wang.
-
NetLLM: Adapting Large Language Models for Networking
Accepted by ACM SIGCOMM, 2024 [CCF-A, Acceptance Ratio: 62 / 366 = 16.9%] paper code slides
Duo Wu, Xianda Wang, Yaqi Qiao, Zhi Wang, Junchen Jiang, Shuguang Cui, Fangxin Wang.
Full List of Publications:
-
CoBel-World: Harnessing LLM Reasoning to Build a Collaborative Belief World for Optimizing Embodied Multi-Agent Collaboration
Under Review [CCF-A] preprint
Zhimin Wang, Shaokang He, Duo Wu, Jinghe Wang, Linjia Kang, Jing Yu, Zhi Wang.
-
CATP-LLM: Empowering Large Language Models for Cost-Aware Tool Planning
Accepted by ICCV 2025 [CCF-A] preprint code
Duo Wu*, Jinghe Wang*, Yuan Meng*, Yanning Zhang, Le Sun, Zhi Wang.
-
Cluster Based Heterogeneous Federated Foundation Model Adaptation and Fine-Tuning
Accepted by AAAI, 2025 [CCF-A] paper
Xianda Wang*, Yingjie Miao*, Duo Wu*, Chenrui Wu, Fangxin Wang.
-
NetLLM: Adapting Large Language Models for Networking
Accepted by ACM SIGCOMM, 2024 [CCF-A] paper code slides
Duo Wu, Xianda Wang, Yaqi Qiao, Zhi Wang, Junchen Jiang, Shuguang Cui, Fangxin Wang.
-
MANSY: Generalizing Neural Adaptive Immersive Video Streaming With Ensemble and Representation Learning
Accepted by IEEE Transactions on Mobile Computing (TMC), 2024 [CCF-A] paper code
Duo Wu, Panlong Wu, Miao Zhang, Fangxin Wang.
-
ILCAS: Imitation Learning-Based Configuration-Adaptive Streaming for Live Video Analytics with Cross-Camera Collaboration
Accepted by IEEE Transactions on Mobile Computing (TMC), 2023 [CCF-A] paper
Duo Wu, Dayou Zhang, Miao Zhang, Ruoyu Zhang, Fangxin Wang, Shuguang Cui.
-
A Comprehensive Survey on Segment Routing Traffic Engineering
Accepted by Digital Communications and Networks (DCN), 2022 [JCR-Q1] paper
Duo Wu, Lin Cui.
STANDARD
-
Information Technology Digital Retina Systems Part 4: Edge Subsystem
Artificial Intelligence Technology Industry Strategic Alliance (AITISA), T/AI 116.4-2025
Duo Wu, Yaowei Wang, Yuan Xue, Wen Ji, Ying Wang, Qingfang Zheng, Xinbei Bai, Zhi Wang, Peng Chen, Le Sun, Yunhong Zhou, Qiben Shan, Jiajun Luo, Jiacheng Jiang, Chen Tang, Yan Lan, Pan Li, Jinyu Yuan, Weisheng Kong, Xiaolin Yang, Changyu Liu, Haijun Liu, Xue Rao, Jiangang Zhou, Rongwei Lu, Shuzhao Xie, Yuan Meng, Xuanti Liu, Wenwu Zhu, Wen Gao.
EXPERIENCE
-
Network Transmission Research Group, ByteDance, Shenzhen
Research Intern, from Jan. 2025 to Oct. 2025.
-
Future Network of Intelligence Institute, CUHKSZ
Research Assistant, from Sep. 2022 to April 2024.
-
Huawei Technologies Co., Ltd., Dongguan
Software Engineer Intern, from July. 2021 to Sep. 2021.
AWARD
-
Presidential Award for Outstanding Graduate Students, CUHKSZ, 2024
Only 10 awardee out of 1500+ postgraduate students in CUHKSZ
-
Academic Star Nomination, JNU, 2021
Only 23 awardee in JNU
-
University Scholarship of Innovative and Talented Undergraduate, JNU, 2021
10000 RMB, only 30 awardee in JNU
SERVICES
Reviewer
-
IEEE Transactions on Mobile Computing
-
IEEE Transactions on Network and Service Management
-
AAAI 2025
-
NeurIPS 2024
-
ACM Multimedia 2023
Teaching Assistant
-
64100033-200 Big Data System (B), 2024 Fall.
-
60250131-200 Lecture Series of Big Data Science and Applications, 2025 Spring.
TALK
-
NetLLM: Adapting Large Language Models for Networking
SIGCOMM, Sydney, Australia, Aug. 6th, 2024.
-
Adapting Large Language Models for Networking
The University of Göttingen, Göttingen, Germany, Virtual, Sept. 23rd, 2024. -
NetLLM: Adapting Large Language Models for Networking recording
AI TIME Youth Talk, Virtual, Oct. 30th, 2024.
CONTACT
Name: Duo Wu (吴铎)
Address: Information Building Tsinghua Campus, University Town of Shenzhen, P. R. China
E-mail: wu-d24@mails.tsinghua.edu.cn / duowu18@outlook.com
Social Media: RedNote 555058144 (Personal); 95575089446 (Group)