Papers3

All Beginner Intermediate Advanced

All Sources arXiv

#Group Relative Policy Optimization

Blockwise Advantage Estimation for Multi-Objective RL with Verifiable Rewards

Intermediate

Kirill Pavlenko, Alexander Golubev et al.Feb 10arXiv

The paper fixes a common mistake in training language models for multi-part tasks: giving the same reward signal to every token, even when different text parts aim at different goals.

#Blockwise Advantage Estimation#Outcome-Conditioned Baseline#Group Relative Policy Optimization

E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models

Intermediate

Shengjun Zhang, Zhang Zhang et al.Jan 1arXiv

This paper shows that when teaching image generators with reinforcement learning, only a few early, very noisy steps actually help the model learn what people like.

#E-GRPO#Group Relative Policy Optimization#Flow Matching

Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward

Intermediate

Peter Chen, Xiaopeng Li et al.Dec 18arXiv

The paper studies why two opposite-sounding tricks in RL for reasoning—adding random (spurious) rewards and reducing randomness (entropy)—can both seem to help large language models think better.

#RLVR#Group Relative Policy Optimization#ratio clipping