This pages provides some resources on recent papers related to the topics of this course, that could help you choose papers to present in class. Also, if you would like to suggest a relevant paper which not in the list, please contact the instructor and/or the TAs (contact info on the course descriptions page).
Research Topics & References
Knowledge Fusion Across Foundation Models
Out-of-Distribution Generalization
Other Resources: Courses, Blogs
Other Relevant Courses on Scaling and Alignment Topics
AGI Safety Fundamentals (2022 AI Safety Fundamentals course at Cambridge)
Jacob Hilton's Deep Learning Curriculum
Scaling bibliography by Gwern
Other recent courses:
Blogs
Scaling: Motivation
Large-Scale Pretrained Models
GPT-3 Language Models are Few-Shot Learners (Paper Explained) - by Yannic Kilcher
GPT-3 Demo: New AI Algorithm Changes How We Interact With Technology
AI Robin Williams 2021 (GPT-3 / GPT 3 / GPT-J-6B) artificial intelligence
On alignment
Alignment Research Center (lead by Paul Christiano) : blog
Concepts Portal: Alignment Terminology
Why AI alignment could be hard with modern deep learning (Ajeya Cotra)
Forecasting Transformative AI from Biological Anchors (Ajeya Cotra)
Draft report on AI timelines (Ajeya Cotra)
The Billion Dollar AI Problem That Just Keeps Scaling (Ajeya Cotra)
What failure looks like (Paul Christiano)
Another (outer) alignment failure story (Paul Christiano)
Plans for AI Future: Different Perspectives
The Alberta Plan for AI Research
Toward Next-Generation Artificial Intelligence