PeopleofSuperintelligence

Researcher

Christopher Ye

Christopher Ye is a theoretical computer scientist whose research studies the computational limits of Transformer attention and high-dimensional geometry. He earned a mathematics degree at Princeton in 2021 and worked as a quantitative analyst in Morgan Stanley's Securitized Products Group before his PhD. His 2024 paper with Barna Saha analyzed attention's memory costs, and his 2025 presentation explored replicability in high-dimensional statistics. In April 2026, he presented an ICLR paper on fast attention; in June 2026, he and his coauthors validated and edited a geometry proof first discovered by ChatGPT 5.5 Pro. As of October 2026, he is a fifth-year PhD student in UC San Diego's CS Theory Group, and during summer 2026 he worked with Morgan Stanley's ML Research Group.

Works
20
Citations
9
h-index
2
Badges

Publication numbers from OpenAlex, as of 19 October 2026.

Timeline

  1. 2021

    Mathematics at Princeton

    At Princeton, he earns an undergraduate mathematics degree in 2021 and works with Gillat Kol.

  2. 2024

    Tight I/O bounds for attention

    With Barna Saha, he publishes an ICML paper on attention's I/O complexity in 2024. The paper proves a lower bound that matches FlashAttention's upper bound for cache sizes of at least d².

  3. April 2025

    Replicability in high dimensions

    At a UC San Diego theory seminar in April 2025, he presents work on the computational and statistical costs of replicability. It covers tasks such as multi-hypothesis testing and mean estimation.

  4. April 2026

    Fast attention at any temperature

    In April 2026, he presents an ICLR paper on fast attention at arbitrary temperatures. The work gives subquadratic algorithms for constant head dimensions and establishes conditional lower bounds.

  5. June 2026

    A geometry lower bound

    In June 2026, he, Barna Saha, and Yinzhan Xu post a SETH-based lower bound for the furthest-pair problem in superconstant dimensions. ChatGPT 5.5 Pro initially discovers the proof; the authors validate and substantially edit it.

  6. 2026

    ML research at Morgan Stanley

    During summer 2026, he works with Mina Dalirrooyfard in Morgan Stanley's ML Research Group.

  7. As of October 2026

    PhD student at UC San Diego

    Before his PhD, he works as a quantitative analyst in Morgan Stanley's Securitized Products Group. As of October 2026, he is a fifth-year PhD student in UC San Diego's CS Theory Group.

Career

  1. 2026Morgan StanleyQuantitative analyst

Education

  1. 2021Princeton UniversityMathematics degree
  2. University of California, San DiegoPhD student

From the biography and OpenAlex affiliations (the years of papers that list the organization), so some years are approximate.

Most-cited works

  1. Faster Approximate All Pairs Shortest Paths2024 · Society for Industrial and Applied Mathematics eBooks · 3 citationsWith Barna Saha
  2. On the Complexity of Algorithms with Predictions for Dynamic Graph Problems2023 · 3 citationsWith Barna Saha and Monika Henzinger
  3. Predicting the Stereoselectivity of Chemical Transformations by Machine Learning2021 · 2 citations
  4. Faster Weighted and Unweighted Tree Edit Distance and APSP Equivalence2025 · ACM Symposium on Theory of Computing (STOC) · 1 citationsWith Barna Saha
  5. Almost Optimal Multiple Source Shortest Paths and Reachability2026 · 0 citationsWith Barna Saha

From OpenAlex, as of 19 October 2026.

  1. Stanford University trained or employed 20 of the 89 AI major-prize winners, more than any other universityIncludes University of California, San Diego. Stanford University trained or employed 20 of the 89 AI major-prize winners, more than any other university. We compare doctorate and employment links for major-prize and best-paper winners.
  2. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes University of California, San Diego. Our estimates of where the people shaping AI studied and where their careers led, from education records in cited biographies.
  3. The company share of AI researchers’ top papers rose from 2% to 32%Includes University of California, San Diego. We estimate where leading AI researchers worked when their most-cited papers appeared. The company share rose from 2% in 1975–1979 to 32% in 2020–2024.
  4. Google has the highest combined h-index among AI organizationsIncludes University of California, San Diego. Our estimates of combined and median h-index at AI organizations, using current affiliations and OpenAlex records.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Christopher Ye yet. Send us a free-licensed photo.

  1. christopher ye czye17.github.io. Checked 19 October 2026.
  2. I/O Complexity of Attention, or How Optimal is FlashAttention? proceedings.mlr.press. Checked 19 October 2026.
  3. Christopher Ye (Theory Seminar) | Computer Science cse.ucsd.edu. Checked 19 October 2026.
  4. Subquadratic Algorithms and Hardness for Attention with Any Temperature proceedings.iclr.cc. Checked 19 October 2026.
  5. Furthest Pair Requires Quadratic Time in Superconstant Dimension under SETH arxiv.org. Checked 19 October 2026.