Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
On the Policy Gradient Foundations of Group Relative Policy Optimization: Credit Assignment, Gradient Sparsity, and Rank Collapse
Amritansh Mishra, Supriyo Chakraborty, Berkcan Kapusuzoglu
Group Relative Policy Optimization (GRPO) eliminates the learned critic in PPO by using the mean reward of grouped rollouts as a baseline. We provide a rigorous derivation of GRPO…
cs.LG2025
Optimizing Reasoning Efficiency through Prompt Difficulty Prediction
Bo Zhao, Berkcan Kapusuzoglu, Kartik Balasubramaniam +3
Reasoning language models perform well on complex tasks but are costly to deploy due to their size and long reasoning traces. We propose a routing approach that assigns each proble…