Xi Chen

About

Xi Chen is a Full Professor and Andre Meyer Faculty Fellow in the Department of Technology, Operations, and Statistics at the NYU Stern School of Business. He holds affiliated faculty appointments at the Courant Institute of Mathematical Sciences and the Center for Data Science, and is a member of the NYU Blockchain Lab. His research interests encompass foundation models, large language models (LLMs), agentic AI, post-training and preference alignment techniques such as RLHF, evaluation and robustness of AI systems, reasoning and memory systems, statistical learning, optimization, scalable systems, and AI applications in operations, digital platforms, and e-commerce. Chen has contributed to the fields of blockchain, Web3, and decentralized ecosystems, focusing on mechanism design, token economics, and AI-driven financial models. He completed a postdoctoral fellowship at the University of California, Berkeley, working with Professor Michael I. Jordan, and earned his PhD from Carnegie Mellon University, along with an MS in Operations Research from the Tepper School of Business at Carnegie Mellon. Throughout his career, Chen has collaborated with major organizations such as Google, Meta, Adobe, JP Morgan, and Bloomberg, receiving competitive research awards for work integrating machine learning, market design, and optimization. His recent achievements include publications in top conferences and journals, recognition as a Fellow of the American Statistical Association and the…

Research topics

• Materials science
• Nanotechnology
• Engineering
• Chemical engineering
• Internal medicine
• Psychology
• Chemistry
• Geology
• Environmental science
• Waste management

Selected publications

• Programmable calculus operations in electromagnetic space using space-time-coding metasurface

  arXiv (Cornell University) · 2026-01-04

  preprintOpen access

  With the rapid advancement of metasurfaces and the increasing demand for programmable metasurfaces to simplify information systems, wave-based computation using metasurfaces has emerged as an attractive research topic. To facilitate the mathematical operations in electromagnetic (EM) space, here we propose a space-time coding metasurface (STCM) system capable of directly performing calculus operations on the spatial energy distributions of EM waves. By exploiting harmonic characteristics induced…

  PublisherDOI

• Programmable calculus operations in electromagnetic space using space-time-coding metasurface

  ArXiv.org · 2026-01-04

  articleOpen access

  With the rapid advancement of metasurfaces and the increasing demand for programmable metasurfaces to simplify information systems, wave-based computation using metasurfaces has emerged as an attractive research topic. To facilitate the mathematical operations in electromagnetic (EM) space, here we propose a space-time coding metasurface (STCM) system capable of directly performing calculus operations on the spatial energy distributions of EM waves. By exploiting harmonic characteristics induced…

  PublisherOA PDF

• Halfspaces are hard to test with relative error

  arXiv (Cornell University) · 2025-11-09

  preprintOpen access1st authorCorresponding

  Several recent works [DHLNSY25, CPPS25a, CPPS25b] have studied a model of property testing of Boolean functions under a \emph{relative-error} criterion. In this model, the distance from a target function $f: \{0,1\}^n \to \{0,1\}$ that is being tested to a function $g$ is defined relative to the number of inputs $x$ for which $f(x)=1$; moreover, testing algorithms in this model have access both to a black-box oracle for $f$ and to independent uniform satisfying assignments of $f$. The motivation…

  PublisherOA PDFDOI

• Model-agnostic super-resolution in high dimensions

  ArXiv.org · 2025-11-11

  preprintOpen access1st authorCorresponding

  The problem of super-resolution, roughly speaking, is to reconstruct an unknown signal to high accuracy, given (potentially noisy) information about its low-degree Fourier coefficients. Prior results on super-resolution have imposed strong modeling assumptions on the signal, typically requiring that it is a linear combination of spatially separated point sources. In this work we analyze a very general version of the super-resolution problem by considering completely general non-negative signals…

  PublisherOA PDFDOI

• MoETTA: Test-Time Adaptation Under Mixed Distribution Shifts with MoE-LayerNorm

  ArXiv.org · 2025-11-14

  preprintOpen access

  Test-Time adaptation (TTA) has proven effective in mitigating performance drops under single-domain distribution shifts by updating model parameters during inference. However, real-world deployments often involve mixed distribution shifts, where test samples are affected by diverse and potentially conflicting domain factors, posing significant challenges even for SOTA TTA methods. A key limitation in existing approaches is their reliance on a unified adaptation path, which fails to account for t…

  PublisherOA PDFDOI

Recent grants

• CAREER: Bridging Game Theory, Economics and Computer Science: Equilibria, Fixed Points, and Beyond

  NSF · $500k · 2012–2017

• Measurement of Mechanical Properties of Small Material Structures by Nanoindentation

  NSF · $255k · 2004–2008

• PECASE: The Science Underpinning Mechanical Self-Assembly

  NSF · $407k · 2007–2013

Frequent coauthors

• Arthur Cukiert

  264 shared

• John Kerrigan

  Centre Hospitalier Universitaire Sainte-Justine

  264 shared

• J. Helen Cross

  Epilepsy Research UK

  264 shared

• Lisa Soeby

  Université de Montréal

  264 shared

• Nathan T. Cohen

  University College London

  264 shared

• Ilene Penn Miller

  Harvard University

  264 shared

• Clifford B. Saper

  Hadassah Medical Center

  264 shared

• Andreas Schulze‐Bonhage

  Stichting Epilepsie Instellingen Nederland

  264 shared

Labs

• Xi Chen LabPI

  Not provided

Education

• Ph.D.

  Carnegie Mellon University

• M.S., Operations Research

  Tepper School of Business

Awards & honors

• Fellow of the American Statistical Association (2025)
• Fellow of the Institute of Mathematical Statistics (IMS) (20…
• Best Paper Award at NeurIPS Workshop on Decentralization and…
• Best Retail Operations and Revenue Management Paper Award at…
• John Birge Best Revenue Management and Market Analytics Pape…

Similar researchers at Columbia University

• Kyunghyun Choh-90
• Gérard Ben Aroush-53
• Chen Fengh-46