Skip to main content

Lecture: Modern Recommendation Systems: When the Academic Meets the Industrial Practice

Dr. Ji Liu: Principal AI scientist at Instagram, Meta Platforms (UW Madison Comp Sci PhD graduate)

Event Details

Date
Monday, December 2, 2024
Time
3-4 p.m.
Location
Description

LIVE STREAM: https://docs.google.com/document/d/1In59vT-MIEg4pjCJgairwP3_n5tz76MSO3MAew7nr88/edit?usp=sharing

Abstract: Recommendation systems have become one of the most critical technologies driving profitability in the internet industry, despite not being the most popular area in academia. This talk will introduce the fundamental components of recommendation systems, their evolution in the data-driven era, and share the speaker’s own attempts and explorations to upgrade the current systems. Key industry advancements will be discussed, including training super large-scale recommendation models (100 trillion parameters), addressing optimal decision-making in recommendation systems, and exploring the relationship between recommendation systems and generative AI.

Additionally, the presentation will offer an academic perspective to formulate the challenges faced in industry, showing a potential approach bridging the gap between academic research and real-world industrial applications.

Bio: Dr. Ji Liu received his PHD from UW-Madison. He is currently the principal AI scientist at Instagram, Meta Platforms Inc. He is also an affiliate professor at University of Washington.

In prior of that, he worked at several leading Chinese internet companies, including Tencent, Kuaishou, and Huawei. He held pivotal roles as Chief/Principal AI Scientist, spearheading the development and leadership of AI teams, after earning his academic credentials from the University of Rochester.

He has been dedicated to developing end-to-end, data-driven systems and solutions to upgrade the current ones for addressing bottleneck challenges in critical industrial scenarios such as recommendation systems, advertising, search, and gaming. One of his notable achievements includes contributing to the development of one of the world’s most scalable recommendation system training frameworks.

With over 100 publications in top-tier CS conferences and journals, he has received multiple best paper and competition awards, and he has also served as an area chair for top CS conferences. His contributions have earned him several prestigious accolades, including the IBM Faculty Award in 2017, recognition as an MIT TR35 Innovator in 2018, and being named one of China’s Top 5 AI Innovators under 35 in 2018.

Cost
Free

Tags