PhD student @ NYU. NLP, synthetic data, and training dynamics.
-
NYU CILVR
- New York, New York
- michahu.github.io/
Highlights
- Pro
Pinned Loading
-
pre-pretraining
pre-pretraining PublicAccelerate pretraining by pre-pretraining on formal languages!
-
modeling-training
modeling-training PublicDirectly model training dynamics, then interpret the dynamics model.
-
on-policy-mix
on-policy-mix PublicEfficient and simple data mixing with on-policy proxies!
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.



