I am… a final-year PhD student at MIT with Antonio Torralba and Phillip Isola. I work on machine learning, representation learning, and reinforcement learning.

Research. I am interested in structures in machine learning and artificial agents, with a focus on structures for more intelligent agents (e.g., invariances to imperceptible changes, distances w.r.t. decision-making capabilities, task-specific factorizations of signal and noise), and extracting and representing such *data structures* with neural nets.

Most of my works are related to these specific topics:

  • Structures as learned representations.

  • Structures for efficient and general agents.

  • Structures of datasets in learning, e.g., what makes for a good training set.

Outside research, I spent my time on developing 1st offering of MIT’s Deep Learning course, GitHub User's stars open-source ML projects, organizing a NeurIPS workshop on Goal-Conditional RL, mentoring SGI students (blog), pro bono office hours (book me!), and with 😸😼.

On 2023-2024 faculty job market: YES ✅

Email: tongzhou _AT_ mit _DOT_ edu

Selected Publications (full list)

Structure as learned representations Structure for better agents Structure of datasets in learning

Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning
[ICML 2023][Project Page] [arXiv] [Code]
Tongzhou Wang, Antonio Torralba, Phillip Isola, Amy Zhang
paper thumbnail Quasimetric Geometry +
Novel Objective
(Push apart s_start & goal
while keeping local dists.)
= Optimal Value V
Goal-Reaching Agents

Improved Representation of Asymmetrical Distances with Interval Quasimetric Embeddings
[NeurIPS 2022 NeurReps Workshop] [Project Page] [arXiv] [PyTorch Package for Quasimetric Learning]
Tongzhou Wang, Phillip Isola

Denoised MDPs: Learning World Models Better Than The World Itself
[ICML 2022] [Project Page] [arXiv] [code]
Tongzhou Wang, Simon S. Du, Antonio Torralba, Phillip Isola, Amy Zhang, Yuandong Tian

On the Learning and Learnability of Quasimetrics
[ICLR 2022] [Project Page] [arXiv] [OpenReview] [code]
Tongzhou Wang, Phillip Isola

Learning to See by Looking at Noise
[NeurIPS 2021] [Project Page] [arXiv] [code & datasets]
Manel Baradad*, Jonas Wulff*, Tongzhou Wang, Phillip Isola, Antonio Torralba

Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere
[ICML 2020] [Project Page] [arXiv] [code]
Tongzhou Wang, Phillip Isola
# bsz : batch size (number of positive pairs)
# d   : latent dim
# x   : Tensor, shape=[bsz, d]
#       latents for one side of positive pairs
# y   : Tensor, shape=[bsz, d]
#       latents for the other side of positive pairs
def align_loss(x, y, alpha=2):
  return (x - y).norm(p=2, dim=1).pow(alpha).mean()
def uniform_loss(x, t=2): return torch.pdist(x, p=2).pow(2).mul(-t).exp().mean().log()
PyTorch implementation of the alignment and uniformity losses

Dataset Distillation
[Project Page] [arXiv] [code] [DD Papers]
Tongzhou Wang, Jun-Yan Zhu, Antonio Torralba, Alexei A. Efros
Meta-Learning MCMC Proposals
[NeurIPS 2018] [PROBPROG 2018] [ICML 2017 AutoML Workshop Oral] [arXiv]
Tongzhou Wang, Yi Wu, David A. Moore, Stuart J. Russell
Learning to Synthesize a 4D RGBD Light Field from a Single Image
[ICCV 2017] [arXiv]
Pratul Srinivasan, Tongzhou Wang, Ashwin Sreelal, Ravi Ramamoorthi, Ren Ng