Weiyu Guo

Weiyu Guo

Ph.D. Candidate, HKUST(GZ)

I am a Ph.D. candidate at the Artificial Intelligence Thrust, Information Hub, The Hong Kong University of Science and Technology, expected to graduate in July 2026. I am supervised by Prof. Hui Xiong (AAAS/IEEE/AAAI/ACM Fellow, Founding Editor-in-Chief of Nature npj AI).

My research focuses on Brain-Inspired Embodied Intelligence, spanning three interconnected layers:

  • Human-Like Sensing — Neural interfaces, surface electromyography (sEMG), and event-driven vision for robust perception
  • Brain-Inspired Neural Architecture — Spiking Neural Networks (SNNs), neuromorphic computing, and cortex-cerebellum-spinal cord hierarchy modeling
  • Action-Grounded Learning — Vision-Language-Action (VLA) models, hierarchical skill learning, and humanoid robotic control

I have published 40+ papers at top international AI conferences including ICML, NeurIPS, ECCV, CVPR, ICLR, AAAI, and journals such as IJCV, JNE, TNSRE, RA-L, THMS. I also serve as the VLA Research Lead at AI² Robotics.

If you are seeking any form of academic cooperation, please feel free to email me at guoweiyu96@gmail.com.

Embodied AI Vision-Language-Action Spiking Neural Networks Neural Interface Neuromorphic Computing Robotic Manipulation

🔥 News

  • 2026.04:   Our StarVLA report has been published!
  • 2026.02:   Our StarVLA reaches 1.7K+ stars on GitHub!
  • 2025.12:   StarVLA selected as one of the Top 10 Most Influential Open-Source Embodied AI Repositories!
  • 2025.10:   One paper accepted at AAAI 2025!
  • 2025.09:   One paper accepted at IJCV 2025! Two papers accepted at NeurIPS 2025!
  • 2025.01:   One paper accepted at ICLR 2025!
  • 2024.09:   One paper accepted at NeurIPS 2024!
  • 2024.07:   One paper accepted at CVPR 2024!

📚 Achievements

  • Published 40+ international papers at top venues (ICML, NeurIPS, CVPR, ECCV, ICLR, AAAI, IJCV, JNE, THMS, RA-L).
  • Applied for 16 patents, including 2 PCT international patents.
  • Co-founded StarVLA: open-source VLA framework with 1.7K+ GitHub stars, adopted by Unitree and Alibaba Qwen, ranked Top 10 Most Influential Embodied AI Repositories 2025.
  • VLA Research Lead at AI² Robotics (valuation exceeding 10 billion RMB).
  • Involved in writing one book chapter (Generalization with Deep Learning) on World Scientific book.
  • Reported by People’s Daily (人民日报), China Central Television (央视新闻), and Guangzhou Daily.
  • Co-founded a neural-interface company with a valuation of over 70 million RMB.

🎓 Education

  • 2022.08 - Present, The Hong Kong University of Science and Technology (Guangzhou), Artificial Intelligence, Ph.D. Candidate
  • 2019.08 - 2022.06, University of Chinese Academy of Sciences, School of Artificial Intelligence, M.S.
  • 2015.09 - 2019.06, Dalian University of Technology, School of Software Engineering, B.S.

🤝 Collaboration & Industry

VLA Research Lead — AI² Robotics · Leading the development and deployment of brain-inspired embodied large models in commercial humanoid robotic products.
Research Associate — Johns Hopkins University (2021.09 – 2022.06) · Supervised by Prof. Alan Yuille (IEEE Fellow). Published at ECCV.
Long-term Collaboration — Prof. Dario Farina, Imperial College London (2019 – Present) · Published papers in JNE, THMS.

📝 Selected Publications

Nature (under review)
sym
  • Guo, Weiyu, He Zhang, Pengteng Li, Tiefu Cai, Ziyang Chen, Jinhui Ye, Yandong Guo, He Xiao, Yongkui Yang, Ying Sun and Hui Xiong. “A Brain-like Embodied Intelligence for Fluid and Fast Reflexive Robotics Control” Nature (Under review) [Preview]
Code base
sym
  • Co-founders and Core Developers, StarVLA is a modular and flexible codebase for developing Vision-Language Model (VLM) to Vision-Language-Action (VLA) models. 1.7K+ stars [Preview] [Report]
NeurIPS 2025
sym
  • Guo, Weiyu, Ziyang Chen, Shaoguang Wang, Jianxiang He, Yijie Xu, Jinhui Ye, Ying Sun, and Hui Xiong. “Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification for Long Video Understanding.” NeurIPS 2025. [Preview]
ICML 2025
sym
  • Guo, Weiyu, Ziyue Qiao, Ying Sun, Yijie Xu, and Hui Xiong. “Revisiting Noise Resilience Strategies in Gesture Recognition: Short-Term Enhancement in Surface Electromyographic Signal Analysis” ICML (2025). [Preview]
NeurIPS 2024
sym
  • Guo, Weiyu, Ying Sun, Yijie Xu, Ziyue Qiao, Yongkui Yang, and Hui Xiong. “SpGesture: Source-Free Domain-adaptive sEMG-based Gesture Recognition with Jaccard Attentive Spiking Neural Network.” NeurIPS (2024). [Preview]
ECCV 2022
sym
  • Guo, Weiyu, Li, Zhaoshuo, Yang, Yongkui, Wang, Zheng, Taylor, Russell H, Unberath, Mathias, Yuille, Alan, Li, Yingwei. “Context-Enhanced Stereo Transformer.” ECCV (2022) [Preview]
JNE
sym
  • Guo, Weiyu, Ma, Chenfei, Wang, Zheng, Zhang, Hang, Farina, Dario, Jiang, Ning, Lin, Chuang. “Long exposure convolutional memory network for accurate estimation of finger kinematics from surface electromyographic signals.” Journal of Neural Engineering 18(2) 026027 (2021). IOP Publishing
THMS 2023
sym
  • Guo, Weiyu, Jiang, Ning, Farina, Dario, Su, Jingyong, Wang, Zheng, Lin, Chuang, Xiong, Hui. “Multi-attention feature fusion network for accurate estimation of finger kinematics from surface electromyographic signals.” IEEE Transactions on Human-Machine Systems 53(3) 512-519 (2023). IEEE

Other Publications

  • Lu, Yunfan, Xu, Yijie, Ma, Wenzong, Guo, Weiyu, Xiong, Hui. “Event camera demosaicing via swin transformer and pixel-focus loss.” CVPR (2024)

  • Guo, Weiyu, Sun, Guoying, He, JianXiang, Shao, Tong, Wang, Shaoguang, Chen, Ziyang, Hong, Meisheng, Sun, Ying, Xiong, Hui. “A Survey of fMRI to Image Reconstruction.” arXiv preprint arXiv:2502.16861 (2025)

  • Lu, Yunfan, Xu, Xiaogang, Lu, Hao, Qian, Yanlin, Li, Pengteng, Yao, Huizai, Yang, Bin, Li, Junyi, Cai, Qianyi, Guo, Weiyu. “SEE: See Everything Every Time–Adaptive Brightness Adjustment for Broad Light Range Images via Events.” arXiv preprint arXiv:2502.21120 (2025)

  • Lin, Chuang, Zhao, Chunxiao, Zhang, Jianhua, Chen, Chen, Jiang, Ning, Farina, Dario, Guo, Weiyu. “Continuous Estimation of Hand Kinematics from Electromyographic Signals based on Power-and Time-Efficient Transformer Deep Learning Network.” IEEE TNSRE (2024). IEEE

  • Chen, Xingjian, Guo, Weiyu, Lin, Chuang, Jiang, Ning, Su, Jingyong. “Cross-subject lifelong learning for continuous estimation from surface electromyographic signal.” IEEE TNSRE (2024). IEEE

  • Zhang, Gaomin, Guo, Weiyu, Xiong, Xi, Guan, Zhongcheng. “A hybrid approach combining data envelopment analysis and recurrent neural network for predicting the efficiency of research institutions.” Expert Systems with Applications 238 (2024). Pergamon

  • Qiao, Ziyue, Xiao, Meng, Guo, Weiyu, Luo, Xiao, Xiong, Hui. “Information filtering and interpolating for semi-supervised graph domain adaptation.” Pattern Recognition 153 (2024). Pergamon

  • Zhang, He, Sun, Ying, Guo, Weiyu, Liu, Yafei, Lu, Haonan, Lin, Xiaodong, Xiong, Hui. “Interactive interior design recommendation via coarse-to-fine multimodal reinforcement learning.” ACM MM (2023)

  • Lin, Chuang, Chen, Xingjian, Guo, Weiyu, Jiang, Ning, Farina, Dario, Su, Jingyong. “A BERT based method for continuous estimation of cross-subject hand kinematics from surface electromyographic signals.” IEEE TNSRE 31 (2022). IEEE

  • Ma, Chenfei, Guo, Weiyu, Zhang, Hang, Samuel, Oluwarotimi Williams, Ji, Xiaopeng, Xu, Lisheng, Li, Guanglin. “A novel and efficient feature extraction method for deep learning based continuous estimation.” IEEE RA-L 6(4) (2021). IEEE

  • Ma, Chenfei, Lin, Chuang, Samuel, Oluwarotimi Williams, Guo, Weiyu, Zhang, Hang, Greenwald, Steve, Xu, Lisheng, Li, Guanglin. “A bi-directional LSTM network for estimating continuous upper limb movement from surface electromyography.” IEEE RA-L 6(4) (2021). IEEE

  • Guo, Weiyu, Ma, Chenfei, Wang, Zheng, Zhang, Hang, Farina, Dario, Jiang, Ning, Lin, Chuang. “Long exposure convolutional memory network for accurate estimation of finger kinematics from surface electromyographic signals.” JNE 18(2) (2021). IOP Publishing

  • Chen, Chao, Guo, Weiyu, Ma, Chenfei, Yang, Yongkui, Wang, Zheng, Lin, Chuang. “sEMG-based continuous estimation of finger kinematics via large-scale temporal convolutional network.” Applied Sciences 11(10) (2021). MDPI

  • Guo, Linlin, Zhang, Hang, Guo, Weiyu, Fang, Jian, Lu, Bingxian, Ma, Chenfei, Li, Guanglin, Lin, Chuang, Wang, Lei. “Deep Learning for Device-free Human Activity Recognition Using WiFi Signals.” Generalization With Deep Learning (2021)

  • Guo, Linlin, Zhang, Hang, Wang, Chao, Guo, Weiyu, Diao, Guangqiang, Lu, Bingxian, Lin, Chuang, Wang, Lei. “Towards CSI-based diversity activity recognition via LSTM-CNN encoder-decoder neural network.” Neurocomputing 444 (2021). Elsevier

  • Wang, Zheng, Wang, Zhuo, Liao, Jian, Chen, Chao, Yang, Yongkui, Dong, Bo, Chen, Weiguang, Chen, Wenxuan, Lei, Ming, Guo, Weiyu. “CNN-DMA: a predictable and scalable direct memory access engine for convolutional neural network.” GLSVLSI (2021)

  • Chen, Wenxuan, Wang, Zheng, Lei, Ming, Dong, Bo, Wang, Zhuo, Yang, Yongkui, Chen, Chao, Guo, Weiyu, Liang, Chen, Zhang, Qian. “Improving system latency of AI accelerator with on-chip pipelined activation preprocessing and multi-mode batch inference.” IEEE AICAS (2021). IEEE

  • Wang, Chao, Guo, Weiyu, Zhang, Hang, Guo, Linlin, Huang, Changcheng, Lin, Chuang. “sEMG-based continuous estimation of grasp movements by long-short term memory network.” Biomedical Signal Processing and Control 59 (2020). Elsevier

  • Guo, Weiyu, Wang, Chao, Lin, Chuang, Wang, Chenrui. “Long short term memory model based continuous estimation of human finger joint angles.” IEEE RCAR (2019). IEEE

  • Zhang, Hang, Wang, Chao, Guo, Weiyu, Guo, Linlin, Lin, Chuang. “DFNN-based gesture recognition with the shift and damage of the HD-sEMG electrodes.” IEEE ROBIO (2019). IEEE

  • Chen, Rui, Chen, YuanZhi, Guo, Weiyu, Chen, Chao, Wang, Zheng, Yang, Yongkui. “SEMG-based gesture recognition using GRU with strong robustness against forearm posture.” IEEE RCAR (2021). IEEE

  • Ma, Chenfei, Guo, Weiyu, Xu, Lisheng, Li, Guanglin. “Finger joint angle estimation based on sEMG signals and deep learning method.” IEEE RCAR (2021). IEEE

  • Wu, Yaqi, Fan, Zhihao, Chu, Xiaofeng, Ren, Jimmy S, Li, Xiaoming, Yue, Zongsheng, Li, Chongyi, Zhou, Shangcheng, Feng, Ruicheng, Dai, Yuekun. “Mipi 2024 challenge on demosaic for hybridevs camera: Methods and results.” CVPR Workshop (2024)

  • Yunfan, LU, Xu, Xiaogang, Hao, LU, Qian, Yanlin, Yang, Bin, Li, Junyi, Cai, Qianyi, Guo, Weiyu, Xiong, Hui. “SEE: See Everything Every Time-Broader Light Range Image Enhancement via Events.”

Selected Patents

  • Training method, training device of continuous motion information prediction model PCT/CN2020/133443
  • Intelligent interactive glove with AI chip, interactive method and storage medium PCT/CN2021/107108
  • Power efficiency test method, adjustment method, computer equipment CN202010389035.4
  • An in-memory computing accelerator and its optimization method CN202011406904.6
  • An automatic optimization method of graph data processing framework CN202011358762.0

🏫 Teaching & Mentorship

Teaching Assistant:

  • AIAA 5037: Advanced Algorithms and Data Structures — HKUST(GZ)
  • AIAA 5031: Introduction to Computing Using Python — HKUST(GZ)
  • HKUST Summer Research Training Program Mentor

Mentored Students:

Jinhui Ye → Ph.D., HKUST
Pengteng Li → Ph.D., HKUST
Wenzhi Li → Ph.D., Cornell University
Guoying Sun → Ph.D., HITSZ
Shu Chen → Ph.D., HKUST
Xingjian Chen → Alibaba Group

🔬 Academic Service

Conference Reviewer: AAAI, NeurIPS, CVPR, ICLR, ICML (20+ papers reviewed)

Journal Reviewer: Scientific Reports, IEEE Robotics and Automation Letters (RA-L)

Invited Speaker: Shenzhen Loop Area Institute — “Brain-Inspired Computing and Embodied Intelligence”

🏅 Awards

  • National Scholarship for Postgraduates, 2021
  • The President Scholarship of CAS, 2021
  • Merit Student of UCAS, 2020
  • Outstanding Graduates of DUT (top 1%), 2019
  • Outstanding Graduates of Liaoning Province (top 1%), 2019
  • Merit Student of DUT, 2018