Scholar
Guobin Shen
Google Scholar ID: Sv-WdBkAAAAJ
Institute of Automation, Chinese Academy of Sciences
Citations & Impact
Citations
594
H-index
13
i10-index
14
Publications
20
Co-authors
13
list available
Publications
Resume (English only)
Academic Achievements
- Two papers accepted by NeurIPS 2025: 'Learning the Plasticity' and 'STEP' evaluation platform
- SpikePack project accepted by ICCV 2025
- Released PandaGuard, a systematic evaluation framework for LLM safety against jailbreaking attacks
- Released CVC, a large-scale Chinese value rule corpus for value alignment of large language models
- Paper on LLM jailbreak antidote accepted by ICLR 2025
- Two papers, 'StressPrompt' and 'DVS data augmentation,' accepted by AAAI 2025
- Multimodal LLM framework paper accepted by NeurIPS 2024
- Paper on SNN efficiency analysis accepted by CVPR 2024 and selected as a highlight paper
- Research on neuro-evolution strategies accepted by PNAS
Research Experience
- During his doctoral studies, he has been involved in multiple research projects, including scalable alignment for large models, interpretability & trustworthy AI, and cognitive science and neuroscience-inspired AI.
Education
- Ph.D.: Institute of Automation, Chinese Academy of Sciences, Advisor: Prof. Yi Zeng
Background
- Guobin Shen is a fifth-year doctoral student at the Institute of Automation, Chinese Academy of Sciences, supervised by Prof. Yi Zeng. His research bridges neuroscience, cognitive science, and AI to develop brain-inspired approaches for building scalable, trustworthy, and safe large-scale models. He focuses on alignment methods, uncertainty quantification, and robustness against failure modes such as jailbreak attacks and hallucinations, aiming to create AI systems that are not only powerful but also interpretable and reliable.
Miscellany
- Actively seeking postdoctoral positions and industry opportunities for Fall 2026
