Zicheng Lin
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper proposes S2L-PO, a framework that uses smaller, naturally diverse models as structured explorers to enhance the policy-level diversity and performance of larger language models during training.
The paper proposes S2L-PO, a framework that uses smaller, naturally diverse models as structured explorers to enhance the policy-level diversity and performance of larger language models during training.
Papers
Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO
Yiming Ren, Yiran Xu, Zicheng Lin, Chufan Shi +7 more
The paper proposes S2L-PO, a framework that uses smaller, naturally diverse models as structured explorers to enhance the policy-level diversity and performance of larger language models during traini…