Vaishnavh Nagarajan

4

Papers

210

Total Citations

1

Affiliations

Affiliations

Google

Papers (4)

Think before you speak: Training Language Models With Pause Tokens

Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction

Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning

The Pitfalls of Next-Token Prediction