🤓 Hey folks! I am Hengyuan Zhang (张恒源). I am a master’s student at Tsinghua University from August 2022, under the supervision of Prof. Yong Jiang and Prof. Yujiu Yang. My current research interests primarily focus on applying Natural Language Processing (NLP) and Data Mining in domain-specific studies (e.g., Finance, Education, and Cognitive Science), hopefully in an interpretable manner. I am also exploring the possibility of enrolling in a Ph.D. program for the Fall of 2025. If there are any opportunities for collaboration, please feel free to reach out to me at your convenience.

🎓 Education

Tsinghua University (清华大学)

• Aug. 2022 - Present, Master’s Degree in Electronic Information, GPA 3.86 / 4.0

Beijing Language and Culture University (北京语言大学)

• Sept. 2018 - Jul. 2022, Bachelor’s Degree in Language Intelligence and Technology, GPA 3.9 / 4.0

💻 Interships

Advanced Innovation Center for Language Resources, Beijing

• Mar. 2019 - Jul. 2022, Research Assistant, working with Cunliang Kong and Liner Yang

Baidu, Search Strategy Lab, Beijing

• Mar. 2021 - Jul. 2021, Engineering Intern, working with Ge Chen

Xiaomi, AI Lab, Beijing

• Mar. 2022 - Sept. 2022, Research Intern, working with Tong Chen and Yanran Li

Tencent, AI Lab, Shenzhen

• Mar. 2023 - Jul. 2023, Research Intern, working with Wei Bi

Sensetime, Research, Shenzhen

• Aug. 2023 - Mar. 2024, Research Intern, working with Fei Tan and Ziqing Yang

Microsoft Research Asia, Natural Language Computing (NLC) Group, Beijing

• Mar. 2024 - Present, Research Intern, working with Haoyang Huang and DongDong Zhang

📚 Preprint

Preprint Mar. 2024

A Question-centric Multi-experts Contrastive Learning Framework for Improving the Accuracy and Interpretability of Deep Sequential Knowledge Tracing Models

Hengyuan Zhang, Zitao Liu, Chenming Shang, Dawei Li, Yong Jiang

[Paper] | [Code] | Data Mining, Recommendation, Education | Journal

Preprint Mar. 2024

Improving Low-Resource Knowledge Tracing Tasks by Supervised Pre-training and Importance Mechanism Fine-tuning

Hengyuan Zhang, Zitao Liu, Shuyan Huang, Chenming Shang, Bojun Zhan, Yong Jiang

[Paper] | [Code] | Data Mining, Recommendation, Education | Journal

📝 Publications

* denotes equal contribution

ACL 2024 Findings

Balancing Speciality and Versatility: a Coarse to Fine Framework for Supervised Fine-tuning Large Language Model

Hengyuan Zhang, Yanru Wu, Dawei Li, Zacc Yang, Rui Zhao, Yong Jiang, Fei Tan

[Paper] | [Code] | Natural Language Processing, Text Generation | CCF-A Conference

CogSci 2024

Understanding Multimodal Deep Neural Networks: A Concept Selection View

Chenming Shang, Hengyuan Zhang, Hao Wen, Yujiu Yang

[Paper] | Computer Vision, Cognitive Science | CCF-B Conference

CVPR 2024

Incremental Residual Concept Bottleneck Model

Chenming Shang, Shiji Zhou, Hengyuan Zhang, Yujiu Yang, Xinzhe Ni, Yuwang Wang

[Paper] | [Code] | Computer Vision, Cognitive Science | CCF-A Conference

EMNLP 2023 Main Conference

Multi-level Contrastive Learning for Script-based Character Understanding

Dawei Li, Hengyuan Zhang, Yanran Li, Shiping Yang

[Paper] | [Code] | Natural Language Processing, Cognitive Science | CCF-B Conference

ACL 2023 BEA

Assisting Language Learners: Automated Trans-Lingual Definition Generation via Contrastive Prompt Learning

Hengyuan Zhang, Dawei Li, Yanran Li, Chenming Shang, Chufan Shi, Yong Jiang

[Paper] | [Code] | Natural Language Processing, Text Generation, Education | CCF-A Conference

AACL 2022 Oral

Fine-grained Contrastive Learning for Definition Generation

Hengyuan Zhang*, Dawei Li*, Shiping Yang, Yanran Li

[Paper] | [Code] | Natural Language Processing, Text Generation, Education | Conference

ACL 2022 Main Conference

Multitasking Framework for Unsupervised Simple Definition Generation

Cunliang Kong, Yun Chen, Hengyuan Zhang, Liner Yang, Erhong Yang

[Paper] | [Code] | Natural Language Processing, Text Generation, Education | CCF-A Conference

NAACL 2022 SemEval

BLCU-ICALL at SemEval-2022 Task 1: Cross-Attention Multitasking Framework for Definition Modeling

Cunliang Kong, Yujie Wang, Ruining Chong, Liner Yang, Hengyuan Zhang, Erhong Yang

[Paper] | [Code] | Natural Language Processing, Text Generation, Education | CCF-B Conference

🏅 Selected Honors and Awards

👉  Tsinghua University College Comprehensive First Class Scholarship (院综合一等奖学金), 2023

👉  National Scholarship (国家奖学金), 2019, 2020, 2021

👉  Outstanding Graduate Student of Beijing (北京市优秀毕业生), 2021

👉  Excellent League Member of Beijing (北京市优秀团员), 2021

👉  Merit Student of Beijing (北京市三好学生), 2021

👉  Meritorious Winner, Interdisciplinary Contest in Modeling (ICM), 2021

👉  Computer Design Competition National- Second Prize, 2020

👉  CUMCM-Beijing Area First Prize, 2020

👉  Xiaomi Third Hacker Marathon Excellence, 2022

👉  Excellent Volunteer in BLCU, 2020

📌 Miscellaneous

• I am actually a person with a strong desire to share. In my spare time, I like writing blogs and sharing experiences on Redbook, Wechat Official Account and Bilibili (阿源的NLP碎碎念). The selected blogs are as follows:
  • Linguistic Regions in the Large Language Model
  • Prevent Catastrophic Forgetting via SoftMask Mechanism
  • The Key Components in Transformer
  • The Evaluation of Instruction Following
  • Skill Localization of Large Language Model
  • iMAge-guided Text GeneratIon with CLIP
  • The Difference between GLM and UL2 Architectures
• I used to be a guitarist 🎸 in a band when I was in high school. Also, I love playing badminton 🏸, table tennis 🏓 and soccer ⚽️. During holidays, I will also seize any opportunity to travel around the world ⛳️.