Yu Ma (马煜) | AI for Finance & Semantic Communication

About

I am a Ph.D. student at Beijing Institute of Technology and Beijing Zhongguancun Academy. My research focuses on AI for finance and token (semantic) communication. I study financial market microstructure, high-frequency and intraday trading, and trading agents, as well as token communication and semantic communication under bandwidth and latency constraints.

I began my doctoral studies in September 2025. At Beijing Institute of Technology, I am advised by Prof. Jun Zhang, a member of the Chinese Academy of Engineering, and Prof. Zhen Gao on token communication and semantic communication. At Beijing Zhongguancun Academy, I am advised by Yitong Duan on AI for finance and agents. I received my bachelor's degree in Computer Science and Technology from Beijing Institute of Technology.

Research

AI for Finance

I study financial market microstructure and AI methods for high-frequency and intraday trading, with an interest in market simulation and trading agents.

Market modeling. Exploring large models for financial market dynamics and high-frequency and intraday trading.
Market simulation and trading agents. Studying market dynamics at the microstructure level and agents that interact with financial markets.

Token (Semantic) Communication

I explore token communication and semantic communication for multimodal information under challenging channel conditions, with an interest in meeting low-latency communication requirements.

Token communication. Large-model-enabled unified multimodal transmission for 6G connectivity across people, devices, and intelligent systems, under low signal-to-noise ratios, limited bit budgets, and latency constraints.
Efficient inference. Model compression and inference acceleration for low-latency communication.

Publications

Publications and preprints.

From Semantic to Token Communication: The Next Paradigm for Large-Model-Driven 6G Intelligent Connectivity

Yu Ma, Zhen Gao, Li Qiao, Xiaoyuan Zhang, Mahdi Boloursaz Mashhadi, Yin Xu, Wenjun Xu, Xiaodong Xu, Kaibin Huang, Jiangzhou Wang, Rahim Tafazolli, Sheng Chen, Tony Q. S. Quek, Ping Zhang

arXiv, 2026 · Survey

arXiv preprint