Chris Yuhao Liu

yliu298 [at] ucsc [dot] edu

I recently graduated from the University of California, Santa Cruz, with a bachelor's degree in computer science. I also work as a researcher at Professor Jeffrey Flanigan’s JLab.

I am currently working on algorithms that can improve the sample complexity of neural networks. I am also interested in learning with less data, out-of-distribution generalization, interpretability of neural networks, and neuroscience.

Blog  /  CV  /  Email  /  Github  /  LinkedIn  /  Twitter

• [2020-12] Here is my blog page.
• [2020-11] I made a list of resources for meta-learning and another one for reinforcement learning.
• [2020-11] I collected a list of useful resources for computer science graduate school application.
• [2020-09] I am excited to tutor the course CSE142 Machine Learning at UC Santa Cruz in the Fall 2020 quarter.
• [2020-06] I joined Professor Jeffrey Flanigan's JLab.

These included publications and preprints.

Achieving Faster Learning Curve through Oracle-Ensemble Querying
Chris Yuhao Liu, Jeffrey Flanigan
2021
Paper in progress

By knowing which examples in a dataset are hard to classify, we can achieve a faster learning curve (sample complexity) by removing those examples using a model-ensemble filtering approach so that less data is needed to reach a higher accuracy. Our method is also particularly effective in removing examples with noisy labels.

These include coursework and side projects.

TAPT: Text Augmentation Using Pre-Trained Transformers With Reinforcement Learning
UC Santa Cruz
2020-07

I fine-tuned a distilled RoBERTa model as a text classifier on the IMDb Large Movie Review Dataset and a GPT-2 (345M) as a text generator using the proximal policy optimization (PPO) framework.

Fine-Tuning GPT-2 to Generate Research Paper Abstracts
UC Santa Cruz
2020-06

I fine-tuned a pre-trained GPT-2 (774M) model using all research paper titles and abstracts under cs.AI, cs.LG, cs.CL, and cs.CV on arXiv and built a machine learning paper abstract generator. The model is hosted by Hugging Face. This project was the winner of the Image/Text Generation Competition for the course CSE142 Machine Learning in Spring 2020.

Sentiment Analysis With Transformers
UC Santa Cruz
2020-06

I fine-tuned a RoBERTa (355M) model using the IMDb dataset and achieved 96.516% accuracy. This project was the winner of the Sentiment Analysis Competition for the course CSE142 Machine Learning in Spring 2020.

This is a fork of Jon Barron's website.