Dear NU Community,
ISSAI invites you to the guest lecture on «Guardrailing AI Systems for Safety and Robustness: A Discrete Optimization Perspective» by Dr. Arman Zharmagambetov, a Research Scientist at Meta AI, on 26 June 2024.
Dr. Zharmagambetov is a Research Scientist at Meta’s Fundamental AI Research (FAIR) lab, specializing in the intersection of machine learning and optimization. His recent work encompasses discrete optimization for foundation models, ML-guided optimization, and Reinforcement Learning. Dr. Zharmagambetov will talk about the role of discrete optimization in developing safe AI systems.
The lecture will cover:
- Deep generative models such as GANs and VAEs;
- The GenCO framework for generating compliant deep generative models;
- AdvPrompter, a novel framework to generate human-readable adversarial prompts in seconds, and how this method can be applied for red-teaming LLMs, ultimately aiding in the development of safe and robust models.
Don’t miss this opportunity to gain insights into cutting-edge AI research!
Date: June 26, 2024
Time: 4:00 PM
Location: Nazarbayev university, C3 block, 1010 room
Online via Google Meet
Контактная информация:
Aliya Mukhidinova, Senior PR Manager at ISSAI, aliya.mukhidinova@nu.edu.kz
