Picture for Junyi Wei

Junyi Wei

Why Larger Language Models Do In-context Learning Differently?

May 30, 2024
Viaarxiv icon

Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning

Add code
Feb 22, 2024
Viaarxiv icon

Provable Guarantees for Neural Networks via Gradient Feature Learning

Oct 19, 2023
Viaarxiv icon

A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed Features

Jun 03, 2022
Viaarxiv icon