Jason Stock's picture

1 4

Jason Stock

stockeh

·

http://www.jasonstock.me

AI & ML interests

generative diffusion, reinforcement learning, interpretability, AI for science

Recent Activity

upvoted an article 18 days ago

Deriving the PPO Loss from First Principles

upvoted a paper 3 months ago

Less is More: Recursive Reasoning with Tiny Networks

authored a paper 3 months ago

Swift: An Autoregressive Consistency Model for Efficient Weather Forecasting

View all activity

Organizations

upvoted an article 18 days ago

Article

Deriving the PPO Loss from First Principles

20 days ago

•

33

upvoted 2 papers 3 months ago

Less is More: Recursive Reasoning with Tiny Networks

Paper • 2510.04871 • Published Oct 6, 2025 • 504

Swift: An Autoregressive Consistency Model for Efficient Weather Forecasting

Paper • 2509.25631 • Published Sep 30, 2025 • 1

upvoted a paper 4 months ago

AERIS: Argonne Earth Systems Model for Reliable and Skillful Predictions

Paper • 2509.13523 • Published Sep 16, 2025 • 7