Yihang Wang ☕️

Yihang Wang

(he/him)

MEng Artificial Intelligence

UCAS

Professional Summary

I am currently a master’s student at the Institute of Computing Technology, Chinese Academy of Sciences, with a research focus on representation learning and information retrieval. I am passionate about exploring fundamental challenges in Natural Language Processing and related areas. I possess strong self-learning capabilities, solid research and engineering practice experience, effective communication skills, and a positive, collaborative attitude. I have also accumulated rich research experience through participation in multiple academic projects.

Education

M.Eng Artificial Intelligence

2025-09-01

University of Chinese Academy of Sciences

B.Eng Artificial Intelligence

2021-09-01
2025-06-01

Beijing University of Posts and Telecommunications

Interests

Artificial Intelligence Natural Language Processing Representation Learning
📚 My Research

My current research interests focus on representation learning and information retrieval, within the broader area of natural language processing.

I am dedicated to developing innovative methods for building more effective and robust representations, and advancing retrieval techniques to better support real-world applications.

Feel free to reach out if you’re interested in collaboration! 😃

Featured Publications
QUITO-X: A New Perspective on Context Compression from the Information Bottleneck Theory featured image

QUITO-X: A New Perspective on Context Compression from the Information Bottleneck Theory

Generative LLM have achieved remarkable success in various industrial applications, owing to their promising In-Context Learning capabilities. However, the issue of long context in …

avatar
Yihang Wang
MDPO: Customized Direct Preference Optimization with a Metric-based Sampler for Question and Answer Generation featured image

MDPO: Customized Direct Preference Optimization with a Metric-based Sampler for Question and Answer Generation

With the extensive use of large language models, automatically generating QA datasets for domain-specific fine-tuning has become crucial. However, considering the multifaceted …

avatar
Yihang Wang
Recent Publications
Recent News

🎉 Two Papers Accepted to ACL 2026 Main Conference!

Our two papers, “Detoxification for LLM: From Dataset Itself” and “Distilling Large Embeddings via Hyperspherical Householder Quantization,” have been accepted to the ACL 2026 Main Conference! 🎉