Foundational Robustness of Foundation Models

NeurIPS 2022 Tutorial - Lectures + Hands-on Exercise

When: December 05, 2022 (8 AM EDT)

Where: Online on

Foundation models adopting the methodology of deep learning with pre-training on large-scale unlabeled data and finetuning with task-specific supervision are becoming a mainstream technique in machine learning. Although foundation models hold many promises in learning general representations and few-shot/zero-shot generalization across domains and data modalities, at the same time they raise unprecedented challenges and considerable risks in robustness and privacy due to the use of the excessive volume of data and complex neural network architectures. This tutorial aims to deliver a Coursera-like online tutorial containing comprehensive lectures, a hands-on and interactive Jupyter/Colab live coding demo, and a panel discussion on different aspects of trustworthiness in foundation models.

Code and slides will be made available here:


IBM Research

Michigan State University


  1. Basics in foundation models and robustness

  2. Deep dive on foundation models for computer vision

  3. Deep dive on foundation models for code

  4. Hands-on code walkthrough

  5. QnA

  6. Panel discussion


IBM Research

Rensselaer Polytechnic Institute

IBM Research

University of Illinois at Urbana-Champaign

Goethe University

Pin-Yu Chen (Moderator)

IBM Research

Contributors to code demos

Michigan State University


Contact to get more information