Yunqiao Yang

Yunqiao Yang (杨昀樵)

I am a 2nd year Ph.D. student at the Multimedia Laboratory (MMLab), The Chinese University of Hong Kong (CUHK), advised by Prof. Hongsheng Li.

I received my B.E. in Electronic Science and Technology from Shanghai Jiao Tong University (SJTU) in 2025.

My research interests lie in Large Language Models (LLMs), specifically focusing on Coding Agents, Mathematical Reasoning, and Reinforcement learning.

🔥 News

Aug 2026 Paper "SlidesGen-Bench: Evaluating Slides Generation via Computational and Quantitative Metrics" accepted to EMNLP 2026 (Main Conference).
Oct 2025 Paper "WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch" accepted as the Oral of NeurIPS 2025.
Aug 2025 Joined MMLab @ CUHK as a Ph.D. student.
June 2025 Graduated from Shanghai Jiao Tong University as an undergraduate student.
Feb 2025 Paper "Probability-Consistent Preference Optimization (PCPO)" accepted to Findings of ACL 2025.

🏆 Honors & Awards

2025 Hong Kong PhD Fellowship Scheme (HKPFS) — Hong Kong Research Grants Council
2025 Shanghai Outstanding Graduate (上海市优秀毕业生), awarded by Shanghai Municipal Education Commission
2022–2024 National Scholarship (国家奖学金, Ministry of Education), received 3 consecutive years

📝 Selected Publications

SlidesGen-Bench: Evaluating Slides Generation via Computational and Quantitative Metrics

Yunqiao Yang*, Wenbo Li*, Houxing Ren*, Zimu Lu, Ke Wang, Zhiyuan Huang, Zhuofan Zong, Mingjie Zhan, Hongsheng Li

Main Conference of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026)

Selected [Paper] [Homepage] [Code] [Dataset]
WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch

Zimu Lu*, Yunqiao Yang*, Houxing Ren*, Haotian Hou, Han Xiao, Ke Wang, Weikang Shi, Aojun Zhou, Mingjie Zhan, Hongsheng Li

Oral of the Thirty-Ninth Annual Conference on Neural Information Processing Systems

Selected [Paper] [Code] [Dataset]
Probability-Consistent Preference Optimization for Enhanced LLM Reasoning

Yunqiao Yang*, Houxing Ren*, Zimu Lu, Ke Wang, Weikang Shi, Aojun Zhou, Junting Pan, Mingjie Zhan, Hongsheng Li

Findings of the Association for Computational Linguistics (ACL), 2025

Selected [Paper] [Code]

💻 Projects & Resources

We open-source the code and datasets for our research to facilitate reproducibility and further exploration.

SlidesGen-Bench

A benchmark for evaluating AI-generated presentations across Content Fidelity, Visual Aesthetics, and Editability, together with the Slides-Align1.5k human preference dataset. [Homepage]
WebGen-Bench

The first benchmark for evaluating LLM-based agents on generating websites from scratch. [Dataset]
PCPO: Preference Optimization Framework

A novel framework that establishes dual quantitative metrics (surface-level correctness & token-level consistency) for preference selection in LLMs.