Pratyush Ranjan Tiwari's picture

Pratyush Ranjan Tiwari PRO

pratyushrt

·

https://www.pratyush.site/

AI & ML interests

Reinforcements Learning, Privacy, Post-training LLMs, SLMs

Organizations

upvoted a paper 8 months ago

Hard Examples Are All You Need: Maximizing GRPO Post-Training Under Annotation Budgets

Paper • 2508.14094 • Published Aug 15, 2025 • 1

upvoted a collection 9 months ago

Anonymizer Model Series

SLMs for semantically similar replacement of PII to provide better end-user privacy. Three model sizes (0.6B, 1.7B, 4B) for different devices. • 3 items • Updated Aug 27, 2025 • 4