Scholar
Haiquan Zhao
Google Scholar ID: V9-CrQ0AAAAJ
Alibaba Group
Citations & Impact
Citations
55
H-index
3
i10-index
1
Publications
12
Co-authors
8
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Publications: 'Towards Coarse-grained Visual Language Navigation Task Planning Enhanced by Event Knowledge Graph' (CIKM 2024), 'ESC-Eval: Evaluating Emotion Support Conversations in Large Language Models' (EMNLP 2024), 'OVEL: Large Language Model as Memory Manager for Online Video Entity Linking' (COLING 2025), '面向视频的细粒度多模态实体链接' (Journal of Software, 2023); Patent: A network asset identification method based on natural language processing feature engineering (Patent No.: CN115733903A). Projects: Long document Keypoint extraction based on chatpdf, Semi-automatic schema construction based on course introduction, Fine-grained multimodal entity linking for video.
Research Experience
- Algorithm Engineer at Alibaba Group's Qwen Team, focusing on Large Language Model (LLM) safety and decoding strategies; Algorithm Intern on Large Language Model data engineering at Tencent; Research Intern on Emotional Intelligence at Shanghai AI Lab; Network asset identification based on natural language processing feature engineering at Huashun Xinan.
Education
- Bachelor's degree: Computer Science and Technology from Wuhan University, 2022; Master's degree: Fudan University (expected 2025), supervised by Prof. Zhixu Li. During this time, collaborated closely with Dr. Xuwu Wang, PhD student Shisong Chen, and independent researcher Jiaan Wang.
Background
- Research interests: natural language processing and large language models, with a particular emphasis on LLM safety and emotion-aware agents. Also conducted research in the area of Multimodal Knowledge Graphs (MMKG).
Miscellany
- Reviewer: ARR 2025; Other projects include backend management project frontend page, reservoir flow query frontend page, alumni second-hand website backend query page, NLP beginner related projects (text classification, sequence annotation, language model, etc.), network protocol text named entity recognition, and entity relationship extraction.
