Me
Yen-Yu Chang
Research Engineer
@ Horizon Robotics
yenyu [at] cs.stanford.edu
Another Me
I love sports, especially basketball and table tennis.

Biography

I am a research engineer at Horizon Robotics. I am generally interested in computer vision, object-oriented learning, multimodal learning, and reinforcement leraning. My recent research focuses on object-centric neural rendering and object-oriented representation learning and reinforcement learning.

I received my Bachelor's degree in Electrical Engineering from National Taiwan University (NTU) in 2018, and my Master's in Electrical Engineering from Stanford University in 2021. I have had the privilege to work with Prof. Li Fei-Fei, Prof. Jiajun Wu, Prof. Leonidas Guibas, Prof. Jure Leskovec, and Prof. Pan Li at Stanford. I also had the pleasure of working with Prof. Ho-Lin Chen, Prof. Shou-De Lin, and Prof. Hung-Yi Lee at NTU. If you would like to learn more about me, please see my [ Résumé ] or contact me at yenyu [at] cs.stanford.edu.

Interests

  • Machine Learning / Deep Learning
  • Computer Vision/ Neural Rendering
  • Reinforcement Learning / Multimodal Learning
  • Structure Learning / Graph Mining

Education

National Taiwan University (NTU)
B.S. in Electrical Engineering, 2018
Stanford University
M.S. in Electrical Engineering, 2021

Timeline & Experiences

2021 Dec. -
Research Engineer @ Horizon Robotics
Representation Learning, Object-oriented Learning, & Reinforcement Learning
2021 Jul. - 2021 Nov.
Research Assistant @ Stanford Vision and Learning Lab (SVL)
Computer Vision, Neural Rendering, and Multimodal Learning
2019 Sep. - 2021 Jun.
EE master student @ Stanford University
Research Assistant @ Stanford Network Analysis Project (SNAP)
- Deep Learning
- Graph Mining
- Anomaly Detection
Research Assistant @ Stanford Vision & Learning Lab (SVL)
- Computer Vision
- Neural Rendering
- Multimodal Learning
Graduate Researcher @ Stanford Geometric Computation Group
- Computer Vision
- 3D Learning
- CAD Model Analysis
Supervisor: Prof. Leonidas Guibas
2019 Jul. - 2019 Sep.
Summer Research Intern @ Stanford Network Analysis Project (SNAP)
2014 - 2018
Undergraduate student & researcher @ NTU
Electrical Engineering department
Game Theory and Molecular Computing Laboratory & Speech Processing and Machine Learning Laboratory
Primary focus:
- Network creation games
- Price of anarchy (PoA)
- Speech enhancement
Computer Science department
Machine Discovery and Social Network Mining Laboratory
Primary focus:
- (Multiagent) Reinforcement learning
- Time series prediction
1996
He was born.

Selected Publications

Point2Cyl: Reverse Engineering 3D Objects from Point Clouds to Extrusion Cylinders

We propose Point2Cyl, a supervised network transforming a raw 3D point cloud to a set of extrusion cylinders. In this work, we introduce a neural network that solves the extrusion cylinder decomposition problem in a geometry-grounded way by first learning underlying geometric proxies. Precisely, our approach first predicts per-point segmentation, base/barrel labels and normals, then estimates for the underlying extrusion parameters in differentiable and closed-form formulations.

CVPR 2022 New Orleans, LA
ObjectFolder 2.0: A Multisensory Object Dataset for Sim2Real Transfer

We present ObjectFolder 2.0, a large-scale, multisensory dataset of common household objects in the form of implicit neural representations that significantly enhances ObjectFolder 1.0 in three aspects. First, our dataset is 10 times larger in the amount of objects and orders of magnitude faster in rendering time. Second, we significantly improve the multisensory rendering quality for all three modalities. Third, we show that models learned from virtual objects in our dataset successfully transfer to their real-world counterparts in three challenging tasks: object scale estimation, contact localization, and shape reconstruction.

CVPR 2022 New Orleans, LA
ObjectFolder: A Dataset of Objects with Implicit Visual, Auditory, and Tactile Representations

We present ObjectFolder, a dataset of 100 virtualized objects that addresses both challenges with two key innovations. First, ObjectFolder encodes the visual, auditory, and tactile sensory data for all objects, enabling a number of multisensory object recognition tasks, beyond existing datasets that focus purely on object geometry. Second, ObjectFolder employs a uniform, object-centric, and implicit representation for each object's visual textures, acoustic simulations, and tactile readings, making the dataset flexible to use and easy to share.

CoRL 2021 (Virtual)
Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks

In this paper we propose Causal Anonymous Walks (CAWs) to inductively represent a temporal network. We further propose a neural-network model CAW-N to encode CAWs, and pair it with a CAW sampling strategy with constant memory and time cost to support online training and inference. CAW-N is evaluated to predict links over 6 real temporal networks and uniformly outperforms previous SOTA methods by averaged 15% AUC gain in the inductive setting. CAW-N also outperforms previous methods in 5 out of the 6 networks in the transductive setting.

ICLR 2021 (Virtual)
F-FADE: Frequency Factorization for Anomaly Detection in Edge Streams

we propose F-FADE, a new approach for detection of anomalies in edge streams, which uses a novel frequency-factorization technique to efficiently model the time-evolving distributions of frequencies of interactions between node-pairs. Our experiments on one synthetic and six real-world dynamic networks show that F-FADE achieves state of the art performance and may detect anomalies that previous methods are unable to find.

WSDM 2021 (Virtual)
A Regulation Enforcement Solution for Multi-agent Reinforcement Learning

In this paper, we proposed a framework to solve the following problem: In a decentralized environment, given that not all agents are compliant to regulations at first, can we develop a mechanism such that it is in the self-interest of non-compliant agents to comply after all. We utilized empirical game-theoretic analysis to justify our method.

AAMAS 2019 Montreal, QC
Designing Non-greedy Reinforcement Learning Agents with Diminishing Reward Shaping

This paper intends to address an issue in multi-agent RL that when agents possessing varying capabilities. We introduce a simple method to train non-greedy agents with nearly no extra cost. Our model can achieve the following goals: non-homogeneous equality, only need local information, cost-effective, generalizable and configurable.

AAAI/ACM conference on AI, Ethics, Society 2018 (Oral) New Orleans, LA
A Memory-Network Based Solution for Multivariate Time-Series Forecasting

Inspired by Memory Network for solving the question-answering tasks, we proposed a deep learning based model named Memory Time-series network (MTNet) for time series forecasting. Additionally, the attention mechanism designed enable MTNet to be interpretable.

preprint
ANS: Adaptive Network Scaling for Deep Rectifier Reinforcement Learning Models

This work provides a thorough study on how reward scaling can affect performance of deep reinforcement learning agents. We also propose an Adaptive Network Scaling framework to find a suitable scale of the rewards during learning for better performance. We conducted empirical studies to justify the solution.

preprint
Heterogeneous Star Celebrity Games

In this paper, we study the problem of heterogeneous star celebrity games. We prove that the PoA is upper bounded by O(n/β) for all heterogeneous star celebrity games. The bound is asymptotically tight even when restricted to the max celebrity game model and matches with the upper bound on the star celebrity game model. We also show that this upper bound is tight for an extension of the bounded distance network creation games.

preprint
[ pdf ]

Honors & Awards

    International

  • Ranked 19th (out of 4180) / KDD CUP - Main Track / 2018
  • Ranked 4th (out of 4180) / KDD CUP - Specialized Prize for long term prediction / 2018

    Domestic

  • Dean's List / National Taiwan University / 2016
  • Finalist (Top 30) / International Physics Olympiad Domestic Final / 2013
Top