Hello there :)

👋 ! I am Jiayi Pan. A rising senior student majored in Computer Science with a minor in Math.

I believe in the power of computation and am broadly interested in research that makes machines more intelligent and human. Particularly, I am interested in leveraging multimodal information to explore areas such as language grounding, embodied AI, and human robot interaction. I am fortunate to work with Dmitry Berenson , Joyce Chai, Fan Wu as a research assistant.

Outside of research, I love reading, arts, sports on water, implementing random ideas, being connected with interesting people. Feel free to contact me and have fun via email :)

Interests
  • Artificial Intelligence
  • Natural Language Processing
  • Computer Vision
  • Robotics
  • Embodied Agent
Education
  • B.S.E in Computer Science with a Minor in Math

    University of Michigan, Ann Arbor, U.S.A.

  • B.S.E in Electrical and Computer Engineering

    Shanghai Jiao Tong University, Shanghai, China

Publications & Manuscripts

(2022). FairEdit: Preserving Fairness in Graph Neural Networks through Greedy Graph Editing. Arxiv.

PDF Cite Code

Research Experience

 
 
 
 
 
Undergraduate Research Assistant
Mar 2022 – Present University of Michigan

Advised by Dmitry Berenson, Glen Chou

  • Summer Undergraduate Research in Engineering
    • Working on enhancing classical planning algorithm with semantic knowledge of language models
 
 
 
 
 
Situated Language and Embodied Dialogue Lab
Undergraduate Research Assistant
Sep 2021 – Present University of Michigan

Advised by Joyce Chai, Ziqiao Ma.

  • Manner understanding & word-acquisition process (come back later to see our result!)
  • SEAGUL Team member in Amazon SimBot Challenge
    • In charge of the perception module: object detection, semantic segmentation, state estimation, depth estimation
 
 
 
 
 
Advanced Network Lab
Undergraduate Research Assistant
May 2020 – Present Shanghai Jiao Tong University

Advised by Fan Wu, Chaoyue Niu.

Responsibilities include:

  • Leader on a project to use knowledge distillation in combination with neural architecture search to achieve efficient inference across different devices and resource constraints

Side Projects

*
A Guided Tour to Neural Radiance Field
A guided tour to neural radiance field, with extensive notes.
Exploiting Language Context and Social Relation for Efficient Federated Learning
A federated learning system that leverages the rich language context and social relation information, achieving highly-competitive performance.
Fairness in Graph Representation Learning
Reimplementation of SOTA algorithms in promoting fairness in Graph Representation Learning
Modular Mars Rover
A modular-designed remote-controlled robotic car with support of robotic arm, 3 DoF camera, solar panel & power bank, replaceable chassis, disco light & sound.
Ray Tracer
A ray-tracing based renderer that supports diffuse illumination, specular lighting, shadows, reflection and refractions.
Robot Localization
Comparison and analysis of Kalman Filter and Particle Filter on a robot localization task in simulated environment.

Selected Honors/Awards

Tang Jun Yuan JI Scholarship
  • 2 out of 100+ students per year | Highest honor for JI’s Dual Degree students
  • Endowed by Cytus Tang Foundation.
John Wu & Jane Sun Excellence Scholarship
  • 15 out of 1000+ students per year | Highest honor for JI undergraduate students
  • Endowed by Mr John Wu and Mrs. Jane Sun.
Fan Xuji Sholarship
  • 10 out of 10000+ students per year | One of the highest honor for SJTU undergraduate students
  • Endowed by various alumni that were supported by Previous President Fan Xuji.
Chunt-sung Research Scholarhip
  • 50 research projects initiate per year | Top undergraduate research program for SJTU students.
  • Endowed by Tesung-Dao Lee and his wife Hui-Chun Chin.
Second Prize in Chinese Physics Olympiad 2017, 2018
  • Top 100 in Sichuan Province

Back in my highschool days, I was really tired of and bored with all the naive coursework. Just for the fun of it, instead, I spent most of my time learning university-level physics and preparing for the CPhO.

This prize might not look big compared to others listed above, but it is exactly where my passion for science starts. After the “failure” in CPhO, I went on to prepare for the College Entrance Examination (GaoKao) and ranked top 0.1% in 2019.

Now as an AI researcher, I still constantly benefit from the training I had for CPhO. Not only for the domain-specific knowledge I learnt, but also on how to think in the first principle, how to approach, build intuition with, and understand complex systems, etc…

Contact

Schedule:


Direct Contact

  • jiayipan AT umich DOT edu