Scholar
Jun Rao
Google Scholar ID: gbhq6EoAAAAJ
Harbin Institute of Technology (Shenzhen)
Citations & Impact
Citations
293
H-index
7
i10-index
7
Publications
19
Co-authors
8
list available
Publications
Resume (English only)
Academic Achievements
- Published over 20 papers in top conferences and international journals including ACL, EMNLP, SIGIR, MM, CIKM, TALLIP, IPM, ToMM, and TMM. Specific publications include 'SeaPO: Strategic Error Amplification for Robust Preference Optimization of Large Language Models' (EMNLP 2025), 'APT: Improving Specialist LLM Performance with Weakness Case Acquisition and Iterative Preference Training' (ACL 2025), 'CommonIT: Commonality-Aware Instruction Tuning for Large Language Models via Data Partitions' (EMNLP 2024), etc.
Research Experience
- Involved in multiple research projects, published numerous papers in areas such as multimodal learning, knowledge distillation, and image-text retrieval.
Education
- Third-year Ph.D. candidate at the School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), co-advised by Min Zhang and Xuebo Liu.
Background
- Research interests include NLP, large language models (LLMs), and knowledge distillation (KD). Long-term research goal is to build socially intelligent embodied agents with the ability to perceive and engage in multimodal human communication. Research focuses on: 1) fundamentals of multimodal learning, specifically the representation, translation, fusion, and alignment of heterogeneous data sources; 2) human-centered language and vision and their applications; 3) real-world deployment efficiency of LLMs.
Miscellany
- Personal interests include research in areas such as multimodal learning, knowledge distillation, and image-text retrieval.
