Yang Li
Research Assistant
Email: liyang@gdiist.cn
Future Directions:
Multi-Agent Brain-Inspired Memory Systems
Personal Profile:
I received my bachelor’s degree from Beijing University of Chinese Medicine in 2022. After graduation, I secured early-stage funding and joined the Shenzhen Innovation & Entrepreneurship Academy as a member of its first cohort, where I conducted entrepreneurial exploration focused on intelligent hardware and AI systems. During this period, I worked on projects including autonomous wheelchairs, whole-home intelligent hardware, and affective companion devices, gaining interdisciplinary experience across system design and applied AI. Following the unsuccessful progression of angel-round financing, I joined Zhipu AI as an algorithm intern. My work primarily involved poetry generation and general text generation tasks, content generation and optimization for SEO scenarios, as well as in-depth participation in data construction and optimization for the code large language model CodeGeeX and data synthesis and training support for ChatGLM. Subsequently, I participated in the RepoAgent sub-project of the XAgent project at the Tsinghua University Natural Language Processing Laboratory (THUNLP), where I was responsible for building a complete Retrieval-Augmented Generation (RAG) framework and contributed to research on multi-agent execution and code management. After the project concluded, I continued contributing to open-source projects within the Hugging Face community and collaborated with Hugging Face and Posts & Telecom Press on a technical book titled Deep Reinforcement Learning in Practice (under review).I later served as a research assistant in Hong Kong, with research interests focusing on hallucination in large language models, multi-agent systems, and large-model reasoning. I am currently working at the Guangdong Institute of Intelligent Science and Technology, where I am involved in one National Major Science and Technology Project and am responsible for the training and development of large language models in the pain-related research direction at the institute.
Academic journal：
[1] CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X (Q. Zheng, X. Xia, X. Zou, Y. Dong, S. Wang, Y. Xue, L. Shen, Z. Wang, A. Wang, et al.). Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023.
[2] Machine Learning Models for Stroke Detection by Observing the Eye-Movement Features Under Five-Color Visual Stimuli in Traditional Chinese Medicine (Q. Lu, J. Deng, Y. Yu, Y. Li, K. Wei, X. Han, Z. Wang, X. Zhang, X. Wang, C. Yan). Journal of Traditional Chinese Medical Sciences, 2023.
[3] CondAmbigQA: A Benchmark and Dataset for Conditional Ambiguous Question Answering (Z. Li, Y. Li, H. Xie, S.J. Qin). arXiv preprint arXiv:2502.01523, 2025.
[4] Ambiguity Processing in Large Language Models: Detection, Resolution, and the Path to Hallucination (Y. Li, Z. Li, K. Hung, W. Wang, H. Xie, Y. Li). Natural Language Processing Journal, 2025.
[5] BMAM: Brain-inspired Multi-Agent Memory Framework(Yang Li, Jiaxiang Liu, Yusong Wang, Yujie Wu, Mingkun Xu)(ACL ARR 2026 January Submission, under review) .
