research
∙
07/27/2023
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
Reinforcement learning from human feedback (RLHF) is a technique for tra...
share
research
∙
03/23/2023
The Quantization Model of Neural Scaling
We propose the Quantization Model of neural scaling laws, explaining bot...
research
∙
10/24/2022
Precision Machine Learning
We explore unique considerations involved in fitting ML models to data w...
research
∙
10/03/2022
Omnigrok: Grokking Beyond Algorithmic Data
Grokking, the unusual phenomenon for algorithmic datasets where generali...
research
∙
05/20/2022
Towards Understanding Grokking: An Effective Theory of Representation Learning
We aim to understand grokking, a phenomenon where models generalize long...
research
∙
12/10/2020
Understanding Learned Reward Functions
In many real-world tasks, it is not possible to procedurally specify an ...
research
∙
10/26/2020