CV

Education

• Ph.D in Computer Science, Beijing Institude of Technology, 2026~2030 (expected)
• M.S. in System Science, Wuhan University of Science and Technology, 2023~2026
• B.S. in Finance, Hubei University of Economics , 2018~2022

Work experience

• Sept 2025 – Nov 2025: Large Language Model Research Intern

  • Eastern Institute of Technology (EIT)
  • Duties included: Research on efficient inference methods for large language models; interpretability analysis of reasoning processes
  • Achievement: First author of a research paper on reasoning interpretability
  • Supervisor: Prof. Xiaoyu Shen

• Apr 2025 – Sept 2025: LLM Algorithm Intern

  • Gongdao Network Technology
  • Duties included: Studying interpretability of spoken text representations across BERT and decoder-only architectures; building automated audio processing pipelines; developing pitch recognition methods for TTS error correction; fine-tuning BGE embedding models for RAG and implementing model distillation engineering

• Sept 2024 – Apr 2025: Research Intern

  • Shenzhen Institute of Advanced Technology (SIAT), Chinese Academy of Sciences
  • Duties included: Participating in multiple LLM research projects; researching AI safety topics including red teaming and jailbreak attacks for LLMs and multimodal models
  • Achievement: First author of a paper on LLM distillation detection, accepted by ACL 2025 (Main Conference); a first-author paper on the topic of LLMs jailbreaking methods is under reviewing.
  • Supervisor: Prof. Min Yang

Publications

Probing the Difficulty Perception Mechanism of Large Language Models

Lee S, Yin Q, Leong C T, et al. Probing the Difficulty Perception Mechanism of Large Language Models[J]. arXiv preprint arXiv:2510.05969, 2025.

MacLight: Multi-scene Aggregation Convolutional Learning for Traffic Signal Control

Lee S, Lyu H, Gong Y, et al. MacLight: Multi-scene Aggregation Convolutional Learning for Traffic Signal Control[J]. arXiv preprint arXiv:2412.15703, 2024.

Counterfactual experience augmented off-policy reinforcement learning

Lee S, Gong Y, Deng C. Counterfactual experience augmented off-policy reinforcement learning[J]. Neurocomputing, 2025, 637: 130017.

Quantification of Large Language Model Distillation

Lee S, Zhou J, Ao C, et al. Quantification of large language model distillation[C]. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025: 4985-5004.

xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking

Lee S, Ni S, Wei C, et al. xjailbreak: Representation space guided reinforcement learning for interpretable llm jailbreaking[J]. arXiv preprint arXiv:2501.16727, 2025.