Chris Hoang

Hello! I am a PhD student in the CILVR lab at NYU Courant advised by Mengye Ren and supported by the NDSEG fellowship. My areas of interest are machine learning and computer vision. My research goal is to advance the visual perception and reasoning capabilities of AI agents to enable them to robustly operate in the complex real world. Towards this end, I am exploring the following directions:

  1. Self-supervised learning methods for in-the-wild visual data
  2. Learning discriminative representations and world models from videos
  3. Multimodal model architectures and training algorithms

Previously, I worked on the systematic equities research team at The Voleon Group as a machine learning engineer. I completed my bachelor's and master's in computer science at the University of Michigan. There, I was fortunate to work with Honglak Lee on reinforcement learning and representation learning, and Michael P. Wellman on multi-agent systems.

profile photo
News

March 2024

I have received the NDSEG Fellowship to support my PhD at NYU!

September 2023

I started my computer science PhD at NYU advised by Mengye Ren!
Publications
PooDLe: Pooled and dense self-supervised learning from naturalistic videos
Alex N. Wang*, Chris Hoang*, Yuwen Xiong, Yann LeCun, Mengye Ren
Preprint, 2024
project page / arXiv

We propose a self-supervised learning framework that combines pooled and dense objectives to learn representations with spatial and semantic understanding from naturalistic videos.

Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning
Chris Hoang, Sungryull Sohn, Jongwook Choi, Wilka Carvalho, Honglak Lee
NeurIPS, 2021
NeurIPS Workshop on Deep Reinforcement Learning, 2020
project page / arXiv / video

We leverage successor features to formulate a graph-based planning framework and goal-conditioned policy, enabling long-horizon goal-reaching in visual environments.

Spoofing the Limit Order Book: A Strategic Agent-Based Analysis
Xintong Wang, Chris Hoang, Yevgeniy Vorobeychik, Michael P. Wellman,
Games, 2021
paper

We use an agent-based model and empirical game-theoretic analysis to study price manipulation in financial markets and propose mitigation mechanisms.

Learning-Based Trading Strategies in the Face of Market Manipulation
Xintong Wang, Chris Hoang, Michael P. Wemman,
ICAIF, 2020
ICML Workshop on AI in Finance, 2019
paper

We design learning-based trading strategies that have improved robustness to market manipulation and evaluate them with agent-based simulation.


Last updated May 28, 2024


Inspired by Jon Barron's website template