Jiayao Zhang

Bio

I have defended my PhD thesis on Principled and Explainable Reasoning involving Natural Languages at The University of Pennsylvania in March 2024 under the supervision of my advisors Dan Roth and Weijie J. Su, where I studied the integration of statistical methods to solve problems in natural language processing. Before joining Penn, I received my Bachelors in Computer Science with First Class Honors from The University of Hong Kong where my advisor was Hubert T.-H. Chan.

Previously, I visited UC Berkeley in 2018 as an intern working with Dawn Song and Bo Li; I interned at the Amazon AWS AI Labs in the summers of 2022 and 2023, working at the Machine Learning & Forecasting Team, mentored by Bernie Wang and was fortunate to work with many scientists and Amazon scholars; I interned at the Allen Institute for AI (AI2) in Spring 2023, at the NLP Team (AllenNLP) mentored by Yanai Elazar and Jesse Dodge.

[Curriculum Vitae]  [Google Scholar]  [PGP Key]

Talks

• Oct 19, 2023: I present a poster at the DIMACS Workshop on Foundation Models, Large Language Models, and Game Theory.
• May 1, 2023: I present (virtually) our FIFA paper at ICLR '23, recording available here.
• Nov 24, 2022: I gave a talk on commonsense causality reasoning at KnowComp at HKUST.
• Nov 10, 2022: I gave a talk on my PhD research at HKUCS Research Seminar.
• July 19, 2022: I present (virtually) our ROCK paper at ICML '22, recording available here.
• Apr 30, 2022: I gave a poster presentation on commonsense casaulity at the MASC-SLL 2022.
• Dec 7, 2021: I present (virtually) our LE-SDE paper at NeurIPS '21, recording available here.

Preprints

	Estimating the Causal Effect of Early ArXiving on Paper Acceptance Y. Elazar*, J. Zhang*, D. Wadden*, B. Zhang, N. A. Smith Technical Report [arXiv]
	Association between author metadata and acceptance: A feature-rich, matched observational study of a corpus of ICLR submissions between 2017-2022 C. Cheng*, J. Zhang*, D. Roth, T. Ye, B. Zhang Technical Report [arXiv]
	Investigating Fairness Disparities in Peer Review: A Language Model Enhanced Approach J. Zhang, H. Zhang, Z. Deng, D. Roth Technical Report [project] [arXiv] [code/data]

Publications

	Towards Reverse Causal Inference on Panel Data: Precise Formulation and Challenges J. Zhang, Y. Park, D. C. Maddix, D. Roth, B. Wang NeurIPS '23 CDS Workshop [abstract] [preprint]
	COLA: Contextualized Commonsense Causal Reasoning from the Causal Inference Perspective Z. Wang, Q. V. Do, H. Zhang, J. Zhang, W. Wang, T. Fang, Y. Song, G. Y. Wong, S. See ACL '23 [arXiv] [code]
	FIFA: Making Fairness More Generalizable in Classifiers Trained on Imbalanced Data Z. Deng, J. Zhang, L. Zhang, T. Ye, Y. Coley, W.J. Su, and J. Zou ICLR '23 [arXiv] [code]
	ROCK: Causal Inference Principles for Reasoning about Commonsense Causality J. Zhang, H. Zhang, W.J. Su, and D. Roth ICML '22 [arXiv] [code]
	Some Reflections on Drawing Causal Inference using Textual Data: Parallels Between Human Subjects and Organized Texts B. Zhang, and J. Zhang First Conference on Causal Learning and Reasoning (CLeaR '22) [arXiv] [OpenReview]
	Imitating Deep Learning Dynamics via Locally Elastic Stochastic Differential Equations J. Zhang, H. Wang, and W.J. Su NeurIPS '21 [paper] [poster] [slides] [code] [OpenReview]
	On the Weak Neural Dependence Phenomenon in Deep Learning J. Zhang, R. Jia, L. Bo, and D. Song NeurIPS '18 DLT Workshop [paper] [poster]
	Grassmannian Learning: Embedding Geometry Awareness in Shallow and Deep Learning J. Zhang, G. Zhu, R. Heath, and K. Huang [arXiv]
	Automatic Recognition of Space-Time Constellations by Learning on the Grassmann Manifold Y. Du, G. Zhu, J. Zhang, and K. Huang IEEE Trans. Signal Processing IEEE Globalcom '18 [arXiv]