Xilong Cheng

Xilong Cheng is a third-year Master’s student at the School of Information and Communication Engineering, Communication University of China, advised by Yunxiao Qin. He has a strong interest in streaming media narratives, cognitive psychology, and behavioral psychology. His research focuses on leveraging AI technologies to build more generalizable role-playing systems, aiming to construct highly realistic social simulation environments.

His current research interests focus on anthropomorphic generative agents, social simulation, human-inspired representation learning, and human–computer interaction (HCI), including but not limited to:

1. Role-playing agents: Investigating the role-playing capabilities of large language models (LLMs) and developing general role-playing agent frameworks that can support research in social sciences and psychology. Specifically, this line of research focuses on: (1) systematic and quantitative evaluation of role-playing abilities in large language models; (2) role-playing agents with long-term memory, long-horizon reasoning, and continual self-evolution; (3) high-fidelity social simulation environments built upon role-playing agents.
2. Human-inspired Representation Learning: Exploring representation learning methods inspired by human cognition and behavioral mechanisms. This work aims to learn temporally structured and embodied representations from first-person videos and multimodal sensory data, enabling applications of large language models (LLMs) in embodied intelligence and robotic systems.
3. Human–Computer Interaction (HCI): Exploring new paradigms of human–computer interaction built upon the aforementioned agent and representation learning technologies. This research investigates how generative agents and embodied systems can enable more natural, efficient, and interpretable human–AI collaboration, and how such systems can be deployed in real-world interactive scenarios.

Meanwhile, he also has a strong interest in reinforcement learning and continual learning techniques for large language models.

Education

• 🎓 M.S. in Information & Communication Engineering, 2023–2026 (estimated)
  Communication University of China · Advisor: Yunxiao Qin
• 🎓 B.S. in Information & Communication Engineering, 2018–2022
  Communication University of China

Publications

1. PsyMem: Fine-grained psychological alignment and Explicit Memory Control for Advanced Role-Playing LLMs
   Xilong Cheng^★, Yunxiao Qin^★,†, Yuting Tan^★, Zhengnan Li, Ye Wang, Hongjiang Xiao^†, Yuan Zhang
   Transactions of the Association for Computational Linguistics

2. Towards Stable Self-Supervised Object Representations in Unconstrained Egocentric Video
   Yuting Tan^★, Xilong Cheng^★, Yunxiao Qin^★,†, Zhengnan Li, Jingjing Zhang^†
   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

3. Structured Guidance or Open-Ended Generation? Boundaries of Co-Creative AI for Screenwriting
   Xilong Cheng^★,§, Qi Zhou^★, Yuting Tan, Ruihan Dong, Yuhao Zhou, Jingbo Ji, Yunxiao Qin^†

4. FSMLP: Modelling Channel Dependencies With Simplex Theory Based Multi-Layer Perceptions In Frequency Domain
   Zhengnan Li, Haoxuan Li, Hao Wang, Jun Fang, Zhichao Chen, Yuting Tan, Xilong Cheng, Yunxiao Qin^†

5. Meta-Tuner: Meta-Trained Node-Specific Transformations for Graph Few-Shot Class-Incremental Learning
   Zhengnan Li, Jun Fang, Junbo Wang, Xilong Cheng, Yuting Tan, Yunxiao Qin^†
   Expert Systems with Applications

6. FTMixer: Frequency and Time Domain Representations Fusion for Time Series Forecasting
   Zhengnan Li, Yuting Tan, Xilong Cheng, Yunxiao Qin^†
   IEEE Signal Processing Letters

_{^★ Equal contribution · ^† Corresponding author · ^§ Project leader}

Interests

Beyond my academic focus on Large Language Models and Role-Playing Language Agents, I also have a strong passion for sports, particularly football and, more recently, tennis. While I see sports as an essential form of relaxation, I equally enjoy streaming media and reading literature on modern psychology, which help me unwind and broaden my perspective.