I am currently a PhD student at the Institute of Automation, Chinese Academy of Sciences, in the Brain Atlas and Brain-Inspired Intelligence Laboratory, under the supervision of Researcher Shan.Yu since 2021. I obtained my Bachelor of Engineering in Mechatronic Engineering from Beijing Institute of Technology, where I studied from 2017 to 2021.

Research Interest

My research is in computational neuroscience and artificial intelligence. Specifically, I am fascinated by the potential of flexible deep learning inspired by the prefrontal cortex and the hippocampus. The prefrontal cortex, key to higher cognitive functions and a cornerstone of intelligence, coupled with the hippocampus’s critical role in memory systems, guides my efforts to develop more brain-like and robust artificial neural networks. Currently, my work is centered on visual reasoning tasks and reinforcement learning. Additionally, I am experimenting with tasks originally designed for primates to assess prefrontal cortex functions on large language models(LLMs), which I find particularly intriguing.

Publications

Hao, Guangfu, Yang Chen, Sainan Qin, Frédéric Alexandre, and Shan Yu. “Self-Organized Context Dependent Processing in Neural Networks.” (IEEE Transactions on Cognitive and Developmental Systems, under review, Available at SSRN 5056172.).

Guangfu Hao, Frederic Alexandre, Shan Yu. Visual Large Language Models Exhibit Human-Level Cognitive Flexibility in the Wisconsin Card Sorting Test (IEEE Transactions on Cognitive and Developmental Systems, accepted on 10-Jul-2025).

Guangfu Hao, Yuhan Zhang, Guoqing Ma, Yang Chen, Frederic Alexandre, Shan Yu. Large Language Models need Episodic Memory (IJCNN 2025).

Guangfu Hao, Haojie Wen, Liangxuna Guo, Yang Chen, Yanchao Bi, Shan Yu. Flexible Tool Selection through Low-dimensional Attribute Alignment of Vision and Language (Nature Communication, under submitted).

Yuhan Zhang, Guoqing Ma, Guangfu Hao, Liangxuan Guo, Yang Chen, Shan Yu. Efficient Reinforcement Learning through Adaptively Pretrained Visual Encoder (AAAI 2025).

Guoqing Ma, Yuhan Zhang, Yuming Dai, Guangfu Hao, Yang Chen, Shan Yu. Clustering-Based Weight Orthogonalization for Stabilizing Deep Reinforcement Learning (IJCNN 2025).

Guoqing Ma, Yuhan Zhang, Liangxuan Guo, Guangfu Hao, Yang Chen, Shan Yu. DPO-LWM: Distilled Policy Optimization with LLM-Based World Model for Task Planning (NeurIPS 2025, under review).

Liu MS, Gao JQ, Hu GY, Hao GF, Jiang TZ, Zhang C, Yu S. MonkeyTrail: A scalable video-based method for tracking macaque movement trajectory in daily living cages. Zool Res. 2022 May 18;43(3):343-351. doi: 10.24272/j.issn.2095-8137.2021.353. PMID: 35301830; PMCID: PMC9113979.