Assistant Professor
Department of Computer Science
Courant Institute of Mathematical Sciences
Center for Data Science (joint)
New York University
Email: mengye@nyu.edu
Tel: +1 (212) 998-3369
Office: 60 5th Ave, Rm 508, New York, NY, 10011
Mengye Ren is an assistant professor of computer science and data science at New York University (NYU). Before joining NYU, he was a visiting faculty researcher at Google Brain Toronto working with Prof. Geoffrey Hinton. He received B.A.Sc. in Engineering Science (2015), and M.Sc. (2017) and Ph.D. (2021) in Computer Science from the University of Toronto, advised by Prof. Richard Zemel and Prof. Raquel Urtasun. From 2017 to 2021, he was also a senior research scientist at Uber Advanced Technologies Group (ATG) and Waabi, working on self-driving vehicles. His research focuses on making machine learning more natural and human-like, in order for AIs to continually learn, adapt, and reason in naturalistic environments.
Areas: machine learning, computer vision, representation learning, meta-learning, few-shot learning, brain & cognitively inspired learning, robot learning, self-driving vehicles
My key research question is: how do we enable human-like, agent-based machine intelligence to continually learn, adapt, and reason in naturalistic environments? Towards this goal of building a more general and flexible AI, my research has centered on developing representation learning and meta-learning algorithms.
Some recent research highlights include:
Naturalistic paradigms for learning representations, classes, and attributes in an online continual data stream and very few labeled examples (few-shot learning FSL): semi-supervised FSL, incremental FSL, online contextualized FSL, attribute FSL, online self-supervised learning
Meta-learning algorithms: contextual prototypical memory, unsupervised prototypical memory, learning regularization functions, learning to reweight examples, graph hypernetworks
Brain and cognitively inspired representation learning: local activity perturbation, local self-supervised learning, self-supervised learning from video, recurrent attention, learning to imitate drawing, divisive normalization
NYU DS-GA 1008 / CSCI-GA 2572: Deep Learning (2024 spring)
NYU CSCI-GA 2565: Machine Learning (2023 fall)
NYU DS-GA 1003: Machine Learning (2023 spring) [website]
Vector Institute: Deep Learning II (2020 fall)
UofT CSC 411: Machine Learning and Data Mining (2019 winter) [website]
2023/06: I am co-organizing Localized Learning Workshop at ICML 2023.
2023/04: One paper is accepted at CogSci 2023.
2023/02: One paper is accepted at CVPR 2023.
2023/01: Two papers are accepted at ICLR 2023.
2022/12: I gave an invited talk at NeurIPS 2022 Meta-Learn workshop.
2022/10: New preprint on biologically plausible learning with local activity perturbation.
2022/10: One paper accepted at MATH-AI workshop at NeurIPS.
2022/10: One paper accepted at MemARI workshop at NeurIPS.
2022/09: I have moved to New York and officially joined NYU.
[Full List] [Google Scholar] [dblp]
Scaling forward gradient with local losses. Mengye Ren, Simon Kornblith, Renjie Liao, Geoffrey Hinton. ICLR, 2023. [arxiv] [code] [html]
Online unsupervised learning of visual representations and categories. Mengye Ren, Tyler R. Scott, Michael L. Iuzzolino, Michael C. Mozer, Richard Zemel. arXiv preprint 2109.05675, 2022. [arxiv] [code] [html]
Self-supervised representation learning from flow equivariance. Yuwen Xiong, Mengye Ren, Wenyuan Zeng, Raquel Urtasun. ICCV, 2021. [arxiv] [html]
SketchEmbedNet: Learning novel concepts by imitating drawings. Alexander Wang*, Mengye Ren*, Richard Zemel. ICML, 2021. [arxiv] [code] [html]
Wandering within a world: Online contextualized few-shot learning. Mengye Ren, Michael L. Iuzzolino, Michael C. Mozer, Richard Zemel. ICLR, 2021. [arxiv] [code] [video]
Probing few-shot generalization with attributes. Mengye Ren*, Eleni Triantafillou*, Kuan-Chieh Wang*, James Lucas*, Jake Snell, Xaq Pitkow, Andreas S. Tolias, Richard Zemel. arXiv preprint 2012.05895, 2020. [arxiv] [video]
LoCo: Local contrastive representation learning. Yuwen Xiong, Mengye Ren, Raquel Urtasun. NeurIPS, 2020. [arxiv] [video]
Multi-agent routing value iteration networks. Quinlan Sykora*, Mengye Ren*, Raquel Urtasun. ICML, 2020. [arxiv] [code] [video]
Incremental few-shot learning with attention attractor networks. Mengye Ren, Renjie Liao, Ethan Fetaya, Richard S. Zemel. NeurIPS, 2019. [arxiv] [code]
Graph hypernetworks for neural architecture search. Chris Zhang, Mengye Ren, Raquel Urtasun. ICLR, 2019. [arxiv]
Learning to reweight examples for robust deep learning. Mengye Ren, Wenyuan Zeng, Bin Yang, Raquel Urtasun. ICML, 2018. [arxiv] [code] [video] [html]
Meta-learning for semi-supervised few-shot classification. Mengye Ren, Eleni Triantafillou*, Sachin Ravi*, Jake Snell, Kevin Swersky, Joshua B. Tenenbaum, Hugo Larochelle, Richard S. Zemel. ICLR, 2018. [link] [arxiv] [code]
End-to-end instance segmentation with recurrent attention. Mengye Ren, Richard S. Zemel. CVPR, 2017. [link] [arxiv] [code] [video]
Exploring models and data for image question answering. Mengye Ren, Ryan Kiros, Richard S. Zemel. NIPS, 2015. [link] [arxiv] [results] [dataset] [code] [question generation]