KDD'23 Tutorial
Towards Next-Generation Intelligent Assistants
Leveraging Large Language Models

The tutorial "Towards Next-Generation Intelligent Assistants leveraging Large Language Models" will be hosted at the KDD 2023, which will take place in Long Beach, CA on Aug 6-10, 2023. 

Abstract

The emergence of AR/VR devices raised many new challenges for building intelligent assistants. The unique requirements have inspired new research directions such as (a) understanding users’ situated multi-modal contexts (e.g. vision, sensor signals) as well as language-oriented conversational contexts, (b) grounding interactions on growing external and internal knowledge graphs, and (c) developing inference models with on-device constraints and privacy-secured methods. 

In this tutorial, we will provide an in-depth walk-through of techniques in the afore-mentioned areas in the recent literature. We aim to introduce techniques for researchers and practitioners who are building intelligent assistants, and inspire research that will bring us one step closer to realizing the dream of building a next generation intelligent assistant.  

Link to slides

Tutorial Speakers

Luna Dong
(Meta Reality Labs)

Zhou Yu
(Columbia University)

Shane Moon
(Meta Reality Labs)

Ethan Xu
(Meta Reality Labs)

Kshitiz Malik

(Meta)

Detailed Schedule

Location: Long Beach Convention & Entertainment Center

10:00 - 10:20 -- Introduction (20 min)

10:20 - 10:45 -- Conversational AI & LLM basics (25 min)

10:45 - 11:45 -- Multi-modal context-aware conversational AI (60 min)

11:45 - 12:45 -- Personalized knowledge-enhanced conversations (60 min)

12:45 - 12:50 --  On-device and federated learning (5 min)

12:50 - 13:00 -- Conclusions and future directions (10 min)