Chunyi Peng

Chunyi Peng

Auto-generated profile, based on publicly available information

Chunyi Peng

Northeastern University, Shenyang, China

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2026 in AI Open
Verified
Journal Article
Open access
ZLZhenghao Liu
Zhenghao Liu
PHPengcheng Huang
Pengcheng Huang
ZXZhipeng Xu
Zhipeng Xu
XLXinze Li
Xinze Li
SLShuliang Liu
Shuliang Liu
GYGe Yu
Ge Yu

19 July 2026
Verified
Conference Paper
Open access
CPChunyi Peng
Chunyi Peng
ZXZhipeng Xu
Zhipeng Xu
ZLZhenghao Liu
Zhenghao Liu
YLYishan Li
Yishan Li
YYYukun Yan
Yukun Yan
MSMaosong Sun
Maosong Sun
Multimodal Retrieval-Augmented Generation (MRAG) has shown promise in mitigating hallucinations in Multimodal Large Language Models (MLLMs) by incorporating external knowledge. However, existing methods typically adhere to rigid retrieval paradigms by mimicking fixed retrieval trajectories and thus fail to fully exploit the knowledge of different retrieval experts through dynamic interaction based on the model's knowledge needs or evolving reasoning states. To overcome this limitation, we introduce Mixture-of-Retrieval Experts (MoRE), a novel framework that enables MLLMs to collaboratively interact with diverse retrieval experts for more effective knowledge exploitation. Specifically, MoRE learns to dynamically determine which expert to engage with, conditioned on the evolving reasoning state. To effectively train this capability, we propose Stepwise Group Relative Policy Optimization (Step-GRPO), which goes beyond sparse outcome-based supervision by encouraging MLLMs to interact with multiple retrieval experts and synthesize fine-grained rewards, thereby teaching the MLLM to fully coordinate all experts when answering a given query. Experimental results on diverse open-domain QA benchmarks demonstrate the effectiveness of MoRE, achieving average performance gains of over 7% compared to competitive baselines. Notably, MoRE exhibits strong adaptability by dynamically coordinating heterogeneous experts to precisely locate relevant information, validating its capability for robust, reasoning-driven expert collaboration. All codes and data are released on https://github.com/OpenBMB/MoRE.