Welcome
I am a final-year Ph.D. student at NYU advised by Leon Bottou and Yann LeCun. I have broad research interests in machine learning, representation learning and out-of-distribution generalization. Recently, I am interested in the principles of efficient out-of-distribution learning, i.e. build systems to help learn board OOD distributions (↑) with limited examples (↓). To achieve this goal, I build Rich Representation Learning to learn rich & diverse features, propose Predictive disentanglement to learn disentangled representations, create Memory Mosaics to handle in-context & long-context learning at inference-time.
Education
Ph.D., Data Science, New York University, Sep. 2020 - present
M.S., Computer Science, Tianjin University, Sep. 2016 - Jan. 2019
B.S., Computer Science, Tianjin University, Sep. 2012 - July. 2016
Experiences
Visiting Researcher, Meta FAIR Lab, Sep 2023 - Present
Research Scientist Intern, Meta FAIR Lab, May 2023 - Aug 2023
Research Intern (AI), Meta FAIR Lab, May 2022 - Oct 2022
Research Intern, Facebook FAIR lab, April 2019 - Aug 2019
Research Assistant, Sorbonne University, Jan 2019 - Mar 2019
Research Intern, Laboratories Hubert Curien, Sep 2017 - Oct 2017
Publications
2024
Jianyu Zhang, Niklas Nolte, Ranajoy Sadhukhan, Beidi Chen, and Léon Bottou. Memory Mosaics. arXiv preprint arXiv:2405.06394 (2024).
Jianyu Zhang, Léon Bottou: Fine-tuning with Very Large Dropout. arXiv preprint arXiv:2403.00946 (2024).
2023
Jianyu Zhang, Léon Bottou: Learning useful representations for shifting tasks and distributions, In 40th International Conference on Machine Learning ICML, 2023
Alexandre Ramé, Kartik Ahuja, Jianyu Zhang, Matthieu Cord, Léon Bottou, and David Lopez-Paz: Model Ratatouille: Recycling diverse models for out-of-distribution generalization, In 40th International Conference on Machine Learning ICML, 2023
2022
Jianyu Zhang, David Lopez-Paz and Léon Bottou: Rich Feature Construction for the Optimization-Generalization Dilemma. In 39th International Conference on Machine Learning ICML, 2022.
2020
Zhengdao Chen, Jianyu Zhang, Martin Arjovsky, and Léon Bottou: Symplectic recurrent neural networks, In International Conference on Learning Representations ICLR, 2020.
Jianyu Zhang, Pierre Roussel, and Bruce Denby: Creating song from lip and tongue videos with a convolutional vocoder. IEEE Access, 9, pp. 13076-13082. 2021
Jianyu Zhang, Jianye Hao, and Françoise Fogelman-Soulié.: Cross-data Automatic Feature Engineering via Meta-learning and Reinforcement Learning. In Pacific-Asia Conference on Knowledge Discovery and Data Mining, pp. 818-829. Springer, Cham, 2020.
Françoise Fogelman‐Soulié, Lanxiang Mei, Jianyu Zhang, Yiming Li, Wen Ge, Yinglan Li, and Qiaofei Ye: Recommender Systems and Attributed Networks. Advances in Data Science: Symbolic, Complex and Network Data, 4, pp. 139-167. 2020
2019
Jianyu Zhang Jianye Hao, Françoise Fogelman-Soulié, and Zan Wang: Automatic feature engineering by deep reinforcement learning. In Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, pp. 2312-2314. 2019.
2018
Jianyu Zhang, and Françoise Fogelman-Soulié: KKbox’s music recommendation challenge solution with feature engineering. In 11th ACM International Conference on Web Search and Data Mining WSDM. 2018.
Jianyu Zhang, Françoise Fogelman-Soulié, and Christine Largeron: Towards automatic complex feature engineering. In International Conference on Web Information Systems Engineering, pp. 312-322. Springer, Cham, 2018.
Teaching
DS-GA.1001 Introduction to Data Science, Fall 2020 / Fall 2021, New York University, Teaching Assistant
CSCI-UA.0310 Basic Algorithms, Spring 2021, New York University (Shanghai), Teaching Assistant