Yunfan Jiang 姜云帆

Email  /  GitHub  /  LinkedIn  /  Google Scholar

My name is Yunfan Jiang and I am an incoming Stanford EE MS student. I was admitted in 2020 but will enroll in September 2021 as I deferred for one year.

I am doing my internship at ByteDance AI Lab Now. Previously, I obtained my bachelor's degree with first-class honors in Electronics & Electrical Engineering, supervised by Dr Chang Liu and Dr Jiabin Jia, at Edinburgh in Summer 2020.

I am eager to pursue a PhD degree in the future and am seeking research opportunities (either voluntary or paid). Feel free to reach out to me if you are interested in my background.

I am generally interested in embodied AI, which enables learning through interaction with environments, and mainly focus on reinforcement learning (RL). Specifically, I am keen on:

• model-free RL algorithms,
• RL reproducibility and replicability, and
• Amazing applications of RL in games, robotics, and other exciting fields.

Toward the overall goal of AI to create intelligent machines, I have studied, researched, and done work in RL, computer vision, and the intersection of machine learning, engineering, and physics. Currently, I am a research intern in deep RL group at ByteDance AI Lab. Our group focuses on game AI and I also research how hierarchical RL can be employed in games to tackle complex tasks with greater sample efficiency and more stability. During Summer 2020, I was glad to collaborate with Jim Fan from Stanford Vision and Learning Lab. We worked on visual control and distributed RL with particular focuses on sim-to-sim and sim-to-real transfer. Before that, I worked as an undergraduate researcher supervised by Dr Chang Liu in Agile Tomography Group at IDCOM. We developed line-of-sight laser imaging systems empowered by deep learning.

This paper subsumes my bachelor thesis.
This is the first time, to the best of our knowledge, that a deep learning-based algorithm for Chemical Species Tomography (CST) has been experimentally validated for simultaneous imaging of multiple critical parameters in reactive flows using a low-complexity optical sensor with severely limited number of laser beams.

This thesis is subsumed by our CSTNet paper.
To the best of my knowledge, it is the first time to verify and demonstrate the feasibility and effectiveness of applying deep learning-based laser tomographic methods on experimental imaging of flame temperature distributions.

Research intern in Deep Reinforcement Learning group.

Jointly awarded to the best two BEng student projects (bachelor thesis) with the most industrial relevance.

The source code of this website can be found here. This page is awesome!
Last update: October 14, 2020