Lightning Talks with 2023 Amazon Fellows

January 25, 2024

In 2021 Amazon and UCLA collaborated to establish the Science Hub for Humanity and Artificial Intelligence. In May 2023, the Science Hub advisory group selected their third group of Amazon Fellows, 11 among 24 nominations, for 2023, all Ph.D. students from the UCLA Samueli School of Engineering.

During the Lightening Talks in Boelter 3400, each fellow presented their research, which spans machine learning, natural language processing, robotics, and beyond, followed by a brief Q&A session. Feel free to review the 2023 Amazon Fellows’ slide decks, below.

2023 Amazon Fellows Lightning Talks Participants

1. Neural Variational Author Topic Process

Ulzee An

Advisor: Sriram Sankararaman

Neural Variational Author Topic Process

2. Insights from GAN Training with Kernal Discriminators

Evan Becker

Advisor: Alyson Fletcher

Insights from GAN Training with Kernel Discriminators

3. Artificial Intelligence for Hemodynamic Analysis of Cardiovascular Medicine

Guorui Chen

Advisor: Jun Chen

Artificial Intelligence for Hemodynamic Analysis of Cardiovascular Medicine

4. Mulit-Agent Reinforcemnt Learning: Asynchronous Communication, Robustness and Privacy

Jiafan He

Advisor: Quanquan Gu

Multi-Agent Reinforcement Learning: Asynchronous Communication, Robustness and Privacy

5. Non-Euclidean Mixture Model for Social Network Embedding

Roshni Iyer

Advisor: Yizhou Sun and Wei Wang

Non-Euclidean Mixture Model for Social Network Embedding

6. Towards a Unified Approach to Detecting Situational Impairments

Xingyu “Bruce” Liu

Advisor: Xiang “Anthony” Chen

Towards a Unified Approach to Detecting Situational Impairments

7. Chameleon: Compositional Reasoning with Large Language Models

Pan Lu

Advisor: Song-Chun Zhu and Kai-Wei Chang

Chameleon: Compositional Reasoning with Large Language Models

8. Predicting Perinatal Depression using Electronic Health Records

Varuni Sarwal

Advisor: Eleazar Eskin

Predicting Perinatal Depression using Electronic Health Records

9. Harnessing Black-Box Control to Boost Commonsense in LMs' Generation

Yufei Tian

Advisor: Nanyun (Violet) Peng

Harnessing Black-Box Control to Boost Commonsense in LMs’ Generation

10. Improving the Trustworthiness and Generalization of Machine Learning Models

Yihan Wang

Advisor: Cho-Jui Hsieh

Improving the generalization and trustworthiness of machine learning models

11. Predicting and Interpreting Energy Barriers of Metallic Glasses with Graph Neural Networks