activity
20242026
most citedExpanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

16 citations · 17 across the 10 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO

Yiran Xu, Yiming Ren, Zicheng Lin +8

We identify a new dimension for enhancing rollout diversity in Group Relative Policy Optimization (GRPO) for LLMs. While GRPO relies on diverse rollouts, prevailing strategies prim…