Madhav S. Baidya

Identifiers

• name variant Madhav S. Baidya 0.60 · backfill

Papers (1)

1. Selective-Advantage Entropy-Adaptive Horizon GRPO: Asymmetric Token-Level Discounting for Efficient Reinforcement Learning of Language Models cs.LG · 2026 · author #3

Mentions

• 2606.05434 #3 · arxiv_oai · confidence 0.70 Madhav S. Baidya

Frequent Coauthors

• Chirag Chawla 1 shared papers
• Rohan Charudatt Salvi 1 shared papers