Ziao Yang 杨子敖

About Me

I expect to graduate in 2027 and am currently on the job market! Feel free to DM me for any opportunities or discussions. You can access my CV here.

I am a final-year Ph.D. candidate in Computer Science at Brandeis University, advised by Prof. Hongfu Liu. My research focuses on data-centric AI and large language models. Previously, I received my B.Eng. from Sun Yat-sen University in 2022.

Throughout my research career, I have had the opportunity to intern at several industry and research organizations, and I have greatly enjoyed these experiences. I have worked with Dr. Vlad Morariu at Adobe Research, Dr. Lei Zhang at Adobe, Dr. Qi Lu at Y Combinator China, and Dr. Jiaxing Zhang at IDEA.

Research Interests

• Large Language Models
• Data-Centric Learning
• Post-Training & Evaluation
• Data Valuation

News

• [May 2026] I joined Adobe Research as a Research Scientist Intern.
• [Mar 2026] Our paper, “Revisit, Extend, and Enhance Hessian-Free Influence Functions”, was published in TMLR.
• [May 2025] I joined Adobe as a Machine Learning Engineer Intern.
• [Nov 2022] Our GTS Qiankunding project at IDEA won the FewCLUE championship.
• [Aug 2022] My team placed in the top 1% of the Tianchi Big Data Competition: AI Helps Strong Convection Weather Forecast, with Jiacheng Wu (CUHK) and Jiahui Hu (NUIST).

Publications

• Revisit, Extend, and Enhance Hessian-Free Influence Functions
  Ziao Yang, Han Yue, Jian Chen, Hongfu Liu
  Transactions on Machine Learning Research (TMLR), 2026
  Paper PDF

• Recontextualizing Famous Quotes for Brand Slogan Generation
  Ziao Yang, Zizhang Chen, Lei Zhang, Hongfu Liu
  Submitted to EMNLP, 2026
  PDF

• Layer-Aware Influence for Online Data Valuation Estimation
  Ziao Yang, Longbo Huang, Hongfu Liu
  Submitted to TPAMI, 2026
  PDF

• On the Inflation of KNN-Shapley Value
  Ziao Yang, Han Yue, Jian Chen, Hongfu Liu
  Submitted to DMLR, 2026
  PDF

• Validation-Induced Shapley Shifts: How Validation Structure Distorts Data Valuation
  Yinan Shen, Ziao Yang, Hongfu Liu
  arXiv preprint, 2026
  PDF

• PTCT: Patches with 3D-Temporal Convolutional Transformer Network for Precipitation Nowcasting
  Ziao Yang, Xiangrui Yang, Qifeng Lin
  PDF

• TCTN: A 3D-Temporal Convolutional Transformer Network for Spatiotemporal Predictive Learning
  Ziao Yang, Xiangrui Yang, Qifeng Lin
  PDF Code

Projects

• Official Implementation of TCTN (100+ GitHub stars)
• Fengshenbang-LM

Awards

• Tianchi Big Data Competition: AI Helps Strong Convection Weather Forecast, Top 1%, Alibaba Group (2022).
• National College Student Innovation Competition: Top 1, Sun Yat-sen University (2022).
• FewCLUE: Champion with GTS Qiankunding (2022).

Personal

Outside research, I am interested in entrepreneurship and in how technical ideas become useful products. Before graduate school, I trained as a competitive swimmer and reached China’s National Level-1 standard; these days, you will usually find me skiing in winter or playing tennis year-round.

Contact

• 知乎
• Email: ziaoyang@brandeis.edu