Experiences
Research
LLM as NER Data Generator
Sep. 2023 - Mar. 2024
GaTech
- Mentored by Prof. Chao Zhang’s group
- Generating diverse and accurate Named Entity Recognition (IE) training datasets with LLMs
-
Proposed step-wise data generation workflow
Parameter-Efficient Personalization
May. 2023 - Dec. 2023
UMich
- In collaboration with Christopher Clarke at CLARITY lab
- To improve performance on subjective classification tasks
- Conducted literature search, Added subjective dataset on irony
- Built PEFT, Adapter and Personalized Head training & evaluation pipelines and ran experiments
Personalized Text Classification Dataset
Jul. 2022 - Oct. 2022
UMich
- In collaboration with Yiping Kang, Ashish Mahendra at CLARITY lab
- Built dataset with timestamped & changing label set for personalized text classification
- Processed in-production user data from Myca productivity tool
- Implemented and conducted experiments for personalization paper in submission
Symbolic Music Generation
Oct. 2021 - Present
UMich
- Mentored by Artem Abzaliev at Language & Information Technologies
- Designing music-theory-inspired compact music representation through melody and bass extraction, for Language-Modeling-based music generation
- Processed 10k+ music files; Conducting experiments with Transformer-XL and Reformer
-
Example input song: Merry Go Round of Life by Joe Hisaishi
-
Example melody & bass extraction output: Merry Go Round of Life by Joe Hisaishi
Heterogeneous Bi-Encoder
Jul. 2022
UMich
- In collaboration with Ashish Mahendra at CLARITY lab
- Investigated independent context and candidate encoders for intent classification
- Advised on implementation and experiments and edited the paper in submission ACL 2022
Zero-Shot Text Classification
Feb. 2022 - Jun. 2022
UMich
- Mentored by Christopher Clarke at CLARITY lab
- Investigated zero-shot classification frameworks; Proposed novel training strategies
- Re-implemented GPT-2 generative framework; Built training & evaluation pipelines and conducted experiments
- Designed illustrations for and wrote sections in ACL 2023 publication
-
Proposed Training Strategies that inject dataset aspect knowledge
-
Out-of-Domain Architecture performances
-
In-Domain/Out-of-domain label overlap correlates with performance
Industry
Front-end Software Engineer Intern
May. 2021 - Jul. 2021
eBay (remote)
- Mentored by Wei Don and Srini at Seller Experience team
- Developed workflow for video upload in item listing tool
- Got an return offer!
Others
Multi-Robot Collaboration Researcher
Sep. 2021 - Dec. 2021
MDP @ UMich
- Mentored by Tyler Toner at Barton Research Group
- “How to get the relative pose between two robots directly (as opposed to global positioning), exploiting capacity of both robots?”
-
HSR Robot laser scan with KUKA robot detected
-
Exhaustive search heatmap illustrating likely relative pose
-
ICP output when initialized with close robot translation guess
ECG Signal Processing Researcher
Sep. 2020 - Apr. 2022
UROP @ UMich
- Mentored by Dr. Mohammed Saeed at Michigan Medicine
- Built a Dash-based web app for viewing & annotating heart ECG signals
-
ECG Visualization & Annotation tool snapshot
- Proposed self-supervised ECG representation learning, inspired by NLP and vision pre-training
- Compiled 50K+ 12-lead ECG records based on publicly-available datasets
- Implemented Vision Transformer for ECG classification
-
ECG ViT Attention Map on a challenging ECG sample
-
ECG ViT supervised classification performance on PTB-XL dataset
Predictive Maintenance Portability Researcher
Jan. 2021 - Apr. 2021
MDP @ UMich
- Mentored by Max Toothman at Barton Research Group
- “Does the prior failure prediction approach generalize well to similar bearing systems?”
-
Credit: previous student Yuntian Zhao
-
Check for normality on degrading indicator: Frequency at maximum amplitude
-
Illustration on moving window for degradation detection
UX/UI Designer & Developer Intern
Mar. 2020 - May 2020
OpptIn (Startup) @ Scranton, PA (remote)
- Brianstormed UI framework with functional widgets to augment location-specific spaces
- Iterated company logo design
- Implemented Android layouts
Bioengineering Imaging Research Assistant
May. 2019 - Jul. 2019
AJC @ UMD
- Mentored by Prof. Yu Chen and Xi Qin
- Collaborated in a group of 6 on refining kidney tubule segmentation annotations
- Studied image texture analysis and segmentation to better differentiate imaging noise
-
Law’s texture analysis output on a kidney imaging sample
Art Museum Experience Researcher & Mentor
Apr. 2019 - May 2020
FIRE @ UMD
- Mentored by Prof. Kyungjin Yoo.
- Developed an ARCore-based Android app that renders art museum paintings in various colors
- Mentored group of 30+ on VR, AR location technologies training and on research proposals
Soldier Intelligence Trainer
Nov. 2018 - Feb. 2019
UMD
- Participated in Prof. Fawzi Emad’s course challenge about AI soldiers in a 2D grid battlefield
- Implemented genetic search for neural network
-
Soldier self-learning by fighting with itself