Pawar

Vaibhav212303

1

·

AI & ML interests

None yet

Recent Activity

updated a Space about 2 months ago

Vaibhav212303/playwright_server

published a Space about 2 months ago

Vaibhav212303/playwright_server

reacted to Jaward's post with 🔥 over 1 year ago

The beauty in GRPO is the fact that it doesn’t care if the rewards are rule-based or learned, the hack: let the data self-normalize— trajectories in a batch compete against their mean, no value model, no extra params, just clean, efficient RL that cuts memory usage by 50%, while maintaining SOTA performance. btw it was introduced 9months prior to R1: arxiv.org/pdf/2402.03300

View all activity

Organizations

None yet

Vaibhav212303 's datasets 1

Vaibhav212303/playwright-tests

Updated Jan 28, 2025 • 5