About

I am a senior student in Honors Computer Science and Mathematics at NYU Courant with GPA ranking 1/375. During my undergraduate, I’ve had the privilege of working with Prof. Oded Regev, Prof. Saining Xie and Prof. He He. I was previously a visiting student at MIT advised by Prof. Josh Tenenbaum and Prof. Tianmin Shu.

Within Natural Language Processing and Computer Vision, I am particularly interested in:

  • Foundation Models: enhance the robustness, truthfulness, and instruction-adherence of foundation models through diverse experiences (e.g., data instances, structured knowledge, embodied experiences).

  • Commonsense Reasoning: understand cause and effect as events unfold, improve reasoning under diverse social and cultural contexts, and advance joint inference across multiple modalities.

  • Embodied AI: leverage foundation models to build embodied agents capable of long-term decision making through planning, reasoning, managing memory, and learning from human and environment feedback.

Besides academics, I enjoy roaming in movies and books. I am an avid reader of history and scientific fiction, as well as a dedicated writer read by more than 16,000,000 times on different platforms. I also enjoy playing “Go”, piano, badminton, hiking and so much more.

News

  • [Jan, 2024] Release the project and code of MMToM-QA.
  • [Dec, 2023] I’m attending NeurIPS 2023. Feel free to reach out if you’d like to have a chat!
  • [July, 2023] Presented our work at AAAI Summer Symposium 2023
  • [May, 2023] I am joining MIT Cocosci and CSAIL as a visiting student
  • [May, 2023] badge released – SOTA diffusion models with 2x speedup
  • [Apr, 2023] Received NYU Computer Science Prize as the top 1 out of 375 students
  • [May, 2022] Received COMAP Scholarship as the top 4 out of 27,205 teams in MCM

Research

publication teaser
MMToM-QA: Multimodal Theory of Mind Question Answering
Chuanyang Jin, Yutong Wu, Jing Cao, Jiannan Xiang, Yen-Ling Kuo, Zhiting Hu, Tomer Ullman, Antonio Torralba, Joshua Tenenbaum, Tianmin Shu
ArXiv 2024
A short version presented at NeurIPS'23 FMDM Workshop.
paper / project / code / benchmark / tweet
publication teaser
Neural Amortized Inference for Nested Multi-agent Reasoning
Kunal Jha, Tuan Anh Le, Chuanyang Jin, Yen-Ling Kuo, Joshua Tenenbaum, Tianmin Shu
AAAI 2024
Oral Presentation at AAAI Summer Symposium 2023.
paper / project / code / slides / supp
publication teaser
Dynamics of RNA Localization to Nuclear Speckles are Connected to Splicing Efficiency
Jinjun Wu*, Yu Xiao*, Yunzheng Liu*, Li Wen, Chuanyang Jin, Shun Liu, Sneha Paul, Chuan He, Oded Regev, Jingyi Fei
BioRxiv 2024
paper

Projects

publication teaser
Fast Diffusion Transformers
DiT models with 2x speedup and 60% less memory, 500+ GitHub Stars.
project
publication teaser
The Cultural Psychology of Large Language Models: Is ChatGPT a Holistic or Analytic Thinker?
Chuanyang Jin*, Songyang Zhang*, Tianmin Shu, Zhihan Cui
ArXiv 2023
paper
publication teaser
Self-Supervised Image Captioning with CLIP
Chuanyang Jin
NeurIPS Self-Supervised Learning Workshop 2023
paper

► Show more projects

Selected Honors & Awards

  • NYU Computer Science Prize for the Most Promising Junior Student (1 person/year), 2023
  • Dean’s Undergraduate Research Fund ($5,000), 2023
  • COMAP Scholarship ($10,000), 2022
  • MAA Award in Mathematical Contest in Modeling (Top 0.1%), 2022
  • Distinguished Honor Roll of American Mathematics Contest (Top 1%), 2020
  • Bronze Medal of Shing-Tung Yau Computer Science Award ($10,000), 2019
  • Finalist of FIRST Robotics Competition World Championship (Top 0.2%), 2019
  • First Prize of Chinese Mathematical Olympiad (Top 0.1%), 2018

© 2023 Chuanyang Jin. All rights reserved.
Powered by Hydejack v9.1.6