Jiacheng Ye

Third-year Ph.D. student Department of Computer Science The University of Hong Kong [Email] [Github] [Google Scholar]

About me

I am a third-year Ph.D. student at the Department of Computer Science in the University of Hong Kong (HKU), supervised by Dr. Lingpeng Kong and Dr. Tao Yu in HKUNLP. I received my Master degree in Fudan University, supervised by Prof. Qi Zhang in FudanNLP Group, and my Bachelor degree in Sun Yat-sen University.

My recent research focuses on below topics:

• Text diffusion

• Complex reasoning and planning

• Interacting and understanding LLMs

• Data synthesis principles

Publications

(*: equal contribution)

Text Diffusion

• Implicit Search via Discrete Diffusion: A Study on Chess
  Jiacheng Ye, Zhenyu Wu, Jiahui Gao, Zhiyong Wu, Xin Jiang, Zhenguo Li, Lingpeng Kong.
  ICLR 2025. [code] [chess-agent]

• Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning
  Jiacheng Ye, Jiahui Gao, Shansan Gong, Lin Zheng, Xin Jiang, Zhenguo Li, Lingpeng Kong.
  ICLR 2025. [code]

• Scaling Diffusion Language Models via Adaptation from Autoregressive Models
  Shansan Gong*, Shivam Agarwal*, Yizhe Zhang, Jiacheng Ye, Lin Zheng, Mukai Li, Chenxin An, Peilin Zhao, Wei Bi, Jiawei Han, Hao Peng, Lingpeng Kong.
  ICLR 2025. [code]

• Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models
  Jiacheng Ye*, Shansan Gong*, Liheng Chen*, Lin Zheng, Jiahui Gao, Han Shi, Chuan Wu, Zhenguo Li, Wei Bi, Lingpeng Kong.
  NeurIPS 2024. [code]

In-context Learning

• Compositional Exemplars for In-context Learning
  Jiacheng Ye, Zhiyong Wu, Jiangtao Feng, Tao Yu, Lingpeng Kong.
  ICML 2023. [code]

• OpenICL: An Open-Source Framework for In-context Learning
  Zhenyu Wu*, YaoXiang Wang*, Jiacheng Ye*, Jiangtao Feng, Jingjing Xu, Yu Qiao, Zhiyong Wu.
  ACL 2023, demo. [code]

• Self-adaptive In-context Learning
  Zhiyong Wu*, Yaoxiang Wang*, Jiacheng Ye*, Lingpeng Kong.
  ACL 2023. [code]

Data Synthesis

• G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model
  Jiahui Gao*, Renjie Pi*, Jipeng Zhang, Jiacheng Ye, Wanjun Zhong, Yufei Wang, Lanqing Hong, Jianhua Han, Hang Xu, Zhenguo Li, Lingpeng Kong.
  ICLR 2025. [code]

• Generating Data for Symbolic Language with Large Language Models
  Jiacheng Ye, Chengzu Li, Lingpeng Kong, Tao Yu.
  EMNLP 2023. [code]

• Self-Guided Noise-Free Data Generation for Efficient Zero-Shot Learning
  Jiahui Gao*, Renjie Pi*, Yong Lin, Hang Xu, Jiacheng Ye, Zhiyong Wu, Xiaodan Liang, Zhenguo Li, Lingpeng Kong.
  ICLR 2023, spotlight. [code]

• ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback
  Jiacheng Ye, Jiahui Gao, Zhiyong Wu, Jiangtao Feng, Tao Yu, and Lingpeng Kong.
  EMNLP-Findings 2022. [code]

• ZeroGen: Efficient Zero-shot Learning via Dataset Generation
  Jiacheng Ye*, Jiahui Gao*, Qintong Li, Hang Xu, Jiangtao Feng, Zhiyong Wu, Tao Yu and Lingpeng Kong.
  EMNLP 2022. [code] [PaperDigest Most Influential Papers]]

Understanding LLMs

• Language Versatilists vs. Specialists: An Empirical Revisiting on Multilingual Transfer Ability
  Jiacheng Ye, Xijia Tao, Lingpeng Kong.
  Preprint. [code]

Before LLMs

• Heterogeneous Graph Neural Networks for Keyphrase Generation
  Jiacheng Ye*, Ruijian Cai*, Tao Gui and Qi Zhang.
  EMNLP 2021. [code]

• Keyphrase Generation with Fine-Grained Evaluation-Guided Reinforcement Learning
  Yichao Luo*, Yige Xu*, Jiacheng Ye, Xipeng Qiu and Qi Zhang.
  EMNLP-Findings 2021. [code]

• TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing
  ACL 2021. [platform] [code] [blog (zh)]

• One2Set: Generating Diverse Keyphrases as a Set
  Jiacheng Ye, Tao Gui, Yichao Luo, Yige Xu, and Qi Zhang.
  ACL 2021. [code] [blog (zh)]

• Leveraging Document-Level Label Consistency for Named Entity Recognition
  Tao Gui*, Jiacheng Ye*, Qi Zhang, Yaqian Zhou, Yeyun Gong, Xuanjing Huang.
  IJCAI 2020. [code]
  

• Uncertainty-Aware Label Refinement for Sequence Labeling
  Tao Gui*, Jiacheng Ye*, Qi Zhang, Zhengyan Li, Zichu Fei, Yeyun Gong and Xuanjing Huang.
  EMNLP 2020. [code]
  

• Constructing Multiple Tasks for Augmentation: Improving Neural Image Classification with K-means Features
  Tao Gui*, Lizhi Qing*, Qi Zhang, Jiacheng Ye, Hang Yan, Zichu Fei and Xuanjing Huang.
  AAAI 2020. [code]
  

Internships

• Nov. 2021 - Jul. 2023
  Research Intern, Shanghai AI Lab.
  Mentor: Lingpeng Kong.
  Research about Pre-trained Language Model and Text Generation.

• Jun. 2021 - Nov. 2021
  Research Intern, Tencent.
  Mentor: Zhihui Lao and Lifeng Wang.
  Research about a better pre-ranking paradigm for Advertising System and Recommendation System.

• Aug. 2018 - Dec. 2018
  Engineer Intern, Netease.
  Worked on data engineering.

Honors & Awards

• Outstanding graduate of Shanghai, Shanghai, 2022.

• National Scholarship (1%), Ministry of Education of China, 2021.

• Glarun Scholarship of CETC-NRIET (5%), Fudan University, 2020.

• The second-grade scholarship (10%), Sun Yat-sen University, 2016/2017/2018.

• The faculty scholarship (10%), Sun Yat-sen University, 2016/2017.

Services

• Conference Reviewer: EMNLP (2022 - 2023), ACL (2022 - 2023), NeurIPS (2023 - 2024), ICLR (2024 - 2025), ICML (2025)