research

* denotes equal contribution.

• Introducing GPT‑5.3‑Codex: Expanding Codex across the full spectrum of professional work on a computer

  OpenAI

  [blog]

• Introducing GPT-5.2: The most advanced frontier model for professional work and long-running agents

  OpenAI

  [blog]

• GPT-5.1: A smarter, more conversational ChatGPT

  OpenAI

  [blog]

• Introducing ChatGPT Atlas

  OpenAI

  [blog]

• Introducing ChatGPT agent: bridging research and action

  OpenAI

  [blog][system card]

• Introducing OpenAI o3 and o4-mini

  OpenAI

  [blog][CUA system card]

• Computer Using Agent: A universal interface for AI to interact with the digital world

  OpenAI

  [blog]

• Introducing Operator

  OpenAI

  [blog][system card]

• Fit Like You Sample: Sample-Efficient Generalized Score Matching from Fast Mixing Diffusions

  Yilong Qin, Andrej Risteski

  COLT 2024
  NeurIPS 2023 M3L Workshop Oral Presentation
  

  [paper][slides][poster]

• Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines

  Yuchen Li, Alexandre Kirchmeyer*, Aashay Mehta*, Yilong Qin*, Boris Dadachev*, Kishore Papineni*, Sanjiv Kumar, Andrej Risteski

  ICML 2024 Main Conference
  ICLR 2024 BGPT Workshop Oral Presentation
  

  [paper]

• Characterizing Out-of-Distribution Error via Optimal Transport

  Yuzhe Lu*, Yilong Qin*, Runtian Zhai, Andrew Shen, Ketong Chen, Zhenlin Wang, Soheil Kolouri, Simon Stepputtis, Joseph Campbell, Katia Sycara

  NeurIPS 2023 Main Conference & OTML Workshop
  

  [paper][slides]

• Powering Comparative Classification with Sentiment Analysis via Domain Adaptive Knowledge Transfer

  Zeyu Li, Yilong Qin*, Zihan Liu*, Wei Wang

  EMNLP 2021 Main Conference Oral Presentation
  

  [paper][code][slides][poster]