Curriculum Vitae

Download PDF

Education

Shanghai University of Finance and Economics, China

Ph.D. Candidate in Management Science and Engineering Sep. 2022 – Jul. 2027 (Expected)

Supervised by Dr. Yun Chen

Bachelor of Computer Science Sep. 2018 – Jul. 2022

Research Interests

Large Language Models (LLMs), Parameter Efficient Fine-Tuning (PEFT), LLM Agents

Technical Skills

Programming Languages: Python, C/C++, SQL
Frameworks & Tools: PyTorch, Hugging Face Transformers, DeepSpeed, vLLM, CUDA, Git

Selected Research Experience

Tsinghua University NLP Lab (THUNLP) & QY Lab, China

Research Intern Sep. 2023 – Jan. 2025

Objective: Research on parameter-efficient fine-tuning and model compression for large language models, supervised by Shuo Wang.
Results: Led LoRA-Flow (ACL 2024), a dynamic LoRA fusion mechanism for generative tasks; collaborated on Delta-CoMe (NeurIPS 2024), training-free delta compression with mixed-precision for LLMs.

Enhancing Text-to-SQL with Fine-Grained Guidance from Pivot Programming Languages (Pi-SQL) Co-First Author

Status: Accepted to Findings of EMNLP 2025
Method & Result: Proposed using pivot programming languages (e.g., Python) as an intermediate representation to provide fine-grained structural guidance for Text-to-SQL generation.
Links: [Paper] | [Code]

Harnessing Minor Singular Components for PEFT (MiLoRA) First Author

Status: Accepted to NAACL 2025
Method & Result: Proposed initializing LoRA adapters with minor singular components of pre-trained weight matrices, reducing interference with existing knowledge while enabling more effective task-specific adaptation.
Links: [Paper] | [Code]

Dynamic LoRA Fusion for LLMs in Generative Tasks (LoRA-Flow) Co-First Author

Status: Accepted to ACL 2024
Method & Result: Designed a dynamic gating mechanism that automatically determines token-level fusion weights across multiple LoRA modules during inference, enabling more flexible multi-task generalization.
Links: [Paper] | [Code]

Full Publications

[1] Pi-SQL: Enhancing Text-to-SQL with Fine-Grained Guidance from Pivot Programming Languages Yongdong Chi*, Hanqing Wang*, Zonghan Yang, Jian Yang, Xiao Yan, Yun Chen, Guanhua Chen. Findings of EMNLP 2025 [Paper][Code]

[2] MALoRA: Mixture of Asymmetric Low-Rank Adaptation for Enhanced Multi-Task Learning Xujia Wang, Haiyan Zhao, Shuo Wang, Hanqing Wang, Zhiyuan Liu. Findings of NAACL 2025 [Paper]

[3] MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning Hanqing Wang, Yixia Li, Shuo Wang, Guanhua Chen, Yun Chen. NAACL 2025 [Paper] [Code]

[4] Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models Bowen Ping, Shuo Wang, Hanqing Wang, Xu Han, Yuzhuang Xu, Yukun Yan, Yun Chen, Baobao Chang, Zhiyuan Liu, Maosong Sun. NeurIPS 2024 [Paper] [Code]

[5] LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks Hanqing Wang*, Bowen Ping*, Shuo Wang, Xu Han, Yun Chen, Zhiyuan Liu, Maosong Sun. ACL 2024 [Paper] [Code]

[6] StyleBART: Decorate Pretrained Model with Style Adapters for Unsupervised Stylistic Headline Generation Hanqing Wang*, Yajing Luo*, Boya Xiong, Guanhua Chen, Yun Chen. Findings of EMNLP 2023 [Paper]

[7] Multilingual Sentence Transformer as A Multilingual Word Aligner Weikang Wang, Guanhua Chen, Hanqing Wang, Yue Han, Yun Chen. Findings of EMNLP 2022 (short) [Paper]

Honors & Awards

Ph.D. Student (2022–Present)

Award	Year
“Academic Star” — Highest honor at SUFE; 5 graduate students selected per year university-wide	Dec. 2025
National PhD Scholarship — Awarded to ~3% of PhD students by the Ministry of Education, China	Sep. 2025
First-Class Academic Scholarship, SUFE	Sep. 2024

Undergraduate (2018–2022)

Award	Year
Outstanding Graduate, SUFE	Jun. 2022
Honorary Bachelor, SUFE	Jun. 2022
First Prize, Chinese Undergraduate Computer Design Competition	Aug. 2021

Others

Member of the University Table Tennis Team and the School Basketball Team.