Ching-Yao Chuang

Researcher, OpenAI
cychuang (at) alum [dot] mit [dot] edu

google scholar / linkedin / X

Researcher at OpenAI, working to make this go right.

Previously, I was a Member of Technical Staff at xAI, where I worked on reasoning and computer-using agents, and prior to that, a Research Scientist at Meta GenAI.

I obtained my Ph.D. from MIT where I was advised by Prof. Antonio Torralba and Prof. Stefanie Jegelka.

things i helped build

  1. GPT 5.5, GPT 5.6
  2. Grok 4, Grok 4.1
  3. Meta Movie Gen

i used to write papers

  1. Learnings from Scaling Visual Tokenizers for Reconstruction and Generation, Hansen-Estruch et al., ICML 2025
  2. Movie Gen: A Cast of Media Foundation Models, Movie Gen Team, Technical Report
  3. Fairy: Fast Parallelized Instruction-Guided Video-to-Video Synthesis, Wu et al., CVPR 2024
  4. Debiasing Vision-Language Models via Biased Prompts, Chuang et al., arXiv Preprint 2023
  5. The Inductive Bias of Flatness Regularization for Deep Matrix Factorization, Gatmiry et al., NeurIPS 2023
  6. InfoOT: Information Maximizing Optimal Transport, Chuang et al., ICML 2023
  7. Tree Mover's Distance: Bridging Graph Metrics and Stability of Graph Neural Networks, Chuang et al., NeurIPS 2022
  8. Robust Contrastive Learning against Noisy Views, Chuang et al., CVPR 2022
  9. Measuring Generalization with Optimal Transport, Chuang et al., NeurIPS 2021 Spotlight
  10. Contrastive Learning with Hard Negative Samples, Robinson et al., ICLR 2021
  11. Fair Mixup: Fairness via Interpolation, Chuang et al., ICLR 2021
  12. Debiased Contrastive Learning, Chuang et al., NeurIPS 2020 Spotlight
  13. Estimating Generalization under Distribution Shifts via Domain-Invariant Representations, Chuang et al., ICML 2020
  14. The Role of Embedding Complexity in Domain-invariant Representations, Chuang et al., ICML 2019 AMTL Workshop
  15. Learning to Act Properly: Predicting and Explaining Affordances from Images, Chuang et al., CVPR 2018
  16. Show, Adapt and Tell: Adversarial Training of Cross-domain Image Captioner, Chen et al., ICCV 2017
  17. Leveraging Video Descriptions to Learn Video Question Answering, Zeng et al., AAAI 2017