Lauren Rodriguez

laurenrodr

5 5

·

AI & ML interests

Into NLP, diffusion models and AI agents.

Recent Activity

upvoted a paper about 5 hours ago

Recovering Reliable Supervision via Critique-Guided On-Policy Distillation

liked a Space 15 days ago

stepfun-ai/StepAudio-3-Music

upvoted a paper 15 days ago

The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation

View all activity

Organizations

None yet

laurenrodr 's models 2

laurenrodr/classification-fast

24.8k • Updated Aug 30 • 6

laurenrodr/tiny-transformer-multitask18

49.6k • Updated Aug 30 • 11