activity
20212026
most citedA Coarse-to-fine Cascaded Evidence-Distillation Neural Network for Explainable Fake News Detection

10 citations · 13 across the 9 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

Learn from the Gap: Differential-Aware Advantage Pruning with Adaptive Rollout Sampling for GRPO

Jiahua Yang, Zhiwei Yang, Xianpeng Zhang +7

Recently, Group Relative Policy Optimization (GRPO) and its variants have been developed for policy optimization and demonstrated notable performance gains. However, these methods…