Search Results for author:
Found 2 papers, 2 papers with code
In-Context Learning Dynamics with Random Binary Sequences
Large language models (LLMs) trained on huge corpora of text datasets demonstrate intriguing capabilities, achieving state-of-the-art performance on tasks they were not explicitly trained for.
Mechanistic Mode Connectivity
We study neural network loss landscapes through the lens of mode connectivity, the observation that minimizers of neural networks retrieved via training on a dataset are connected via simple paths of low loss.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
