SHILONG DENG's picture

3 9

SHILONG DENG

zczlsde

·

zczlsde

AI & ML interests

RL, NLP

Recent Activity

authored a paper 18 days ago

A Unified Framework for Rethinking Policy Divergence Measures in GRPO

upvoted a paper 18 days ago

A Unified Framework for Rethinking Policy Divergence Measures in GRPO

updated a model 4 months ago

View all activity

Organizations

Papers 5

arxiv:2602.05494

arxiv:2510.00967

arxiv:2501.17282

arxiv:2401.09334

models 1

zczlsde/qwen

Updated Oct 14, 2025

datasets 1

zczlsde/EFG

Viewer • Updated Jul 24, 2024 • 6k • 3