While LLMs offer powerful reasoning and generalization capabilities for user understanding and long-term planning in recommendation systems, their latency and cost hinder direct application in large-scale industrial settings. The talk will cover our recent work on scalable hybrid approaches that combine LLMs and traditional recommendation models. We’ll explore their effectiveness in tackling challenges like cold-start recommendations and enhancing user exploration.
Speaker Bio
Jianling Wang is a senior research scientist working at Google DeepMind. She obtained her Ph.D. degree from the Department of Computer Science and Engineering at Texas A&M University, advised by Prof. James Caverlee. Her research interests generally include data mining and machine learning, with a particular focus on recommendation systems and graph neural networks.
More Details
- When: Mon 9 Dec 2024, at 1 - 2 pm (Brisbane time)
- Speaker: Dr Jianling Wang (Google Deepmind)
- Host: Dr Ruihong Qiu
- Zoom: https://uqz.zoom.us/j/83289875914 [No recording will be provided.]
No.24-18 Developing Effective Long-Context Language Models