Tutorial
Foundational Robustness of Foundation Models
Pin-Yu Chen · Sijia Liu · Sayak Paul
Moderator : Jessica Schrouff
Virtual
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.
Schedule
Mon 5:00 a.m. - 5:30 a.m.
|
Basics in foundation model and robustness
(
tutorial part 1
)
>
SlidesLive Video |
Pin-Yu Chen · Sijia Liu 🔗 |
Mon 5:30 a.m. - 5:55 a.m.
|
Deep dive on foundation models for computer vision
(
tutorial part 2
)
>
SlidesLive Video |
Pin-Yu Chen 🔗 |
Mon 5:55 a.m. - 6:20 a.m.
|
Deep dive on foundation models for code
(
tutorial part 3
)
>
|
Sijia Liu 🔗 |
Mon 6:20 a.m. - 6:50 a.m.
|
Hands-on Jupyter Notebook/Colab walkthrough
(
tutorial part 4
)
>
SlidesLive Video |
Sayak Paul 🔗 |
Mon 6:50 a.m. - 7:00 a.m.
|
Q & A
(
questions
)
>
SlidesLive Video |
Sayak Paul · Sijia Liu · Pin-Yu Chen 🔗 |
Mon 7:00 a.m. - 7:05 a.m.
|
Break to welcome panellists
|
🔗 |
Mon 7:05 a.m. - 7:30 a.m.
|
Panel
(
Panel
)
>
SlidesLive Video |
Pin-Yu Chen · Alex Gittens · Bo Li · Celia Cintas · Hilde Kuehne · Payel Das 🔗 |