I am a PhD student in computer science at Beijing Institute of Technology. I previously majored in finance and systems science, thus holding a Bachelor’s degree in Economics and a Master’s degree in Science.

My main focus is on cutting-edge artificial intelligence technologies such as large language models. My research areas include model distillation, content saferty, and interpretability. In the future, I am inclined to study post-training of models and reinforcement learning training techniques.

Publication

📄 First Author

• Probing the Difficulty Perception Mechanism of Large Language Models
  • arXiv preprint arXiv:2510.05969, 2025
  • Sunbowen Lee, Qingyu Yin, Chak Tou Leong, Jialiang Zhang, Yicheng Gong, Shiwen Ni, Min Yang, Xiaoyu Shen
• Quantification of large language model distillation
  • ACL main, 2025
  • Sunbowen Lee, Junting Zhou, Chang Ao, Kaige Li, Xeron Du, Sirui He, Haihong Wu, Tianci Liu, Jiaheng Liu, Hamid Alinejad-Rokny, et al.
• xjailbreak: Representation space guided reinforcement learning for interpretable LLMs jailbreaking
  • arXiv preprint arXiv:2501.16727, 2025
  • Sunbowen Lee, Shiwen Ni, Chi Wei, Shuaimin Li, Liyang Fan, Ahmadreza Argha, Hamid Alinejad-Rokny, Ruifeng Xu, Yicheng Gong, Min Yang
• Counterfactual experience augmented off-policy reinforcement learning
  • Neurocomputing, 2024
  • Sunbowen Lee, Yicheng Gong, Chao Deng
• MacLight: Multi-scene Aggregation Convolutional Learning for Traffic Signal Control
  • AAMAS main, 2025
  • Sunbowen Lee, Hongqin Lyu, Yicheng Gong, Yingying Sun, Chao Deng
  • 2024

👥 Collaboration

• Finding RELIEF: Shaping Reasoning Behavior without Reasoning Supervision via Belief Engineering
  • ACL Findings, 2026
  • Chak Tou Leong, Dingwei Chen, Heming Xia, Qingyu Yin, Sunbowen Lee, Jian Wang, Wenjie Li
• Evaluating Parameter Efficient Methods for RLVR
  • arXiv preprint arXiv:2512.23165, 2025
  • Qingyu Yin, Yulun Wu, Zhennan Shen, Sunbowen Lee, Zhilin Wang, Yanshu Li, Chak Tou Leong, Jiale Kang, Jinjin Gu
• PoolingVQ: A VQVAE Variant for Reducing Audio Redundancy and Boosting Multi-Modal Fusion in Music Emotion Analysis
  • arXiv preprint arXiv:2509.11976, 2025
  • Dinghao Zou, Yicheng Gong, Xiaokang Li, Xin Cao, Sunbowen Lee
• Emoanti: audio anti-deepfake with refined emotion-guided representations
  • arXiv preprint arXiv:2509.10781, 2025
  • Xiaokang Li, Yicheng Gong, Dinghao Zou, Xin Cao, Sunbowen Lee

🔬 Internship Experience

• Tencent | Applied Research (April 2026 - )

• Eastern Institute of Technology (EIT) | Large Language Model Research Intern (Sept 2025 – Nov 2025)
  • Research Focus: Efficient inference for LLMs under Prof. Xiaoyu Shen.
  • Achievement: First author of a research paper on interpretability of reasoning.
• Gongdao Network Technology | LLM Algorithm Intern (Apr 2025 – Sept 2025)
  • Interpretability: Studied spoken text representation patterns across BERT and Decoder-only architectures.
  • Audio Engineering: Built automated audio processing pipelines and developed pitch recognition for TTS error correction.
  • NLP Optimization: Fine-tuned BGE embedding models for RAG and implemented model distillation engineering.
• Shenzhen Institute of Advanced Technology (SIAT), CAS | Research Intern (Sept 2024 – Apr 2025)
  • Collaboration: Contributed to multiple LLM research initiatives within Prof. Min Yang’s team.
  • AI Safety: Researched Red Teaming and jailbreak attacks for LLMs and Multimodal models (ARR under review).
  • Key Publication: First Author of a paper on LLM distillation detection, accepted by ACL 2025 (Main Conference).