About Me
I am a fourth-year Ph.D student in College of Computer Science and Technology, Zhejiang University, advised by Jianling Sun and Chenghao Liu. Currently I am an intern in Alibaba Qwen (通义千问) group. My research interests are as follows:
- Large generative models, including LLMs for code [9-11], prompting in NLP [6] and graph [5], and diffusion models [Proj.2].
- Time series processing [7-8].
- Unbiased ranking and recommendation [1-4, Proj.1]。
Publications
1. LLMs for Code
[11] 🔥 B4: Towards Optimal Assessment of Plausible Code Solutions with Plausible TestsMouxiang Chen, Zhongxin Liu, He Tao, Yusu Hong, David Lo, Xin Xia, Jianling Sun
ASE 2024: Accepted as a Full Paper.
[10] JumpCoder: Go Beyond Autoregressive Coder via Online Modification
Mouxiang Chen, Hao Tian, Zhongxin Liu, Xiaoxue Ren, Jianling Sun
ACL 2024: Accepted as a Main Conference Paper.
[9] Self-Explained Keywords Empower Large Language Models for Code Generation
Lishui Fan, Mouxiang Chen, Zhongxin Liu
2. Time Series Processing
[8] 🔥 VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series ForecastersMouxiang Chen, Lefei Shen, Zhuo Li, Xiaoyun Joy Wang, Jianling Sun, Chenghao Liu
[7] Calibration of Time-Series Forecasting: Detecting and Adapting Context-Driven Distribution Shift
Mouxiang Chen, Lefei Shen, Han Fu, Zhuo Li, Jianling Sun, Chenghao Liu
KDD 2024: Accepted as a Research Track Paper.
3. Soft Prompting in Graph and NLP
[6] 🔥 Build a Good Human-Free Prompt Tuning: Jointly Pre-trained Template and Verbalizer for Few-shot ClassificationMouxiang Chen, Han Fu, Chenghao Liu, Xiaoyun Joy Wang, Zhuo Li, Jianling Sun
TKDE 2025: Accepted as a Regular Paper. [To appear]
[5] ULTRA-DP: Unifying Graph Pre-training with Multi-task Graph Dual Prompt
Mouxiang Chen, Zemin Liu, Chenghao Liu, Jundong Li, Qiheng Mao, Jianling Sun
4. Unbiased Ranking
[4] Identifiability Matters: Revealing the Hidden Recoverable Condition in Unbiased Learning to RankMouxiang Chen, Chenghao Liu, Zemin Liu, Zhuo Li, Jianling Sun
ICML 2024: Accepted as a Full Paper.
[3] LBD: Decouple Relevance and Observation for Individual-Level Unbiased Learning to Rank
Mouxiang Chen, Chenghao Liu, Zemin Liu, Jianling Sun
NeurIPS 2022: Accepted as a Full Paper.
[2] Scalar is Not Enough: Vectorization-based Unbiased Learning to Rank
Mouxiang Chen, Chenghao Liu, Zemin Liu, Jianling Sun
KDD 2022: Accepted as a Research Track Paper.
[1] Adapting Interactional Observation Embedding for Counterfactual Learning to Rank
Mouxiang Chen, Chenghao Liu, Jianling Sun, Steven C.H. Hoi
SIGIR 2021: Accepted as a Full Paper.
Selected Projects
[Proj.2] MuG Diffusion: High-quality and controllable charting AI (150M parameters) for rhythm games, modifed from stable diffusion.
[Proj.1] AlphaOsu!: A personalized level recommendation system for players on a popular rhythm game osu!.
Selected Award
- 2024, Best Research Award in Data Science (Top 1%)
- 2022, National Scholarship (Top 1%)
- 2019, China Collegiate Computing Contest Second-Class Prize (Top 2%)
- 2019, Contemporary Undergraduate Mathematical Contest in Modeling National Second-Class Prize (Top 3%)
- 2019, Zhejiang Provincial Government Scholarship
- 2018, Zhejiang Province Physics Competition First-Class Prize (Top 5%)
Services
Reviewer at ICML 2025, NeurIPS 2023, ICLR 2024-2025, TheWebConf 2024-2025, KDD 2024.Education
Zhejiang University (Sep. 2021 - Now)- Ph.D Candidate, Computer Science and Technology
- B.S., Computer Science and Technology, Thesis advisor: Jianling Sun
- Major GPA: 4.61/5.00, rank: 16/154
Engineering Experiences
ByteDance, Android R&D Intern (Feb. 2020 - Jul. 2021) StepBeats, Android R&D (May. 2018 - Oct. 2018)- Responsible for Android development of StepBeats, an Application that generating AI-composed music while running.