Author

Junjie Peng

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

COSMO: Consensus-Driven Shift Modulation for Source-Free Domain Adaptation

COSMO replaces expert-to-expert guidance with co-adaptation through an anchored shared consensus and achieves state-of-the-art performance under matched VLM backbones, indicating that it better balances the retention of valid source-derived evidence with the absorption of complementary VLM evidence.

Bo Li, Junjie Peng, Xiaohua Xie et al. · 0 citations

#natural language process... May 2026

GRKV: Global Regression for Training-Free KV Cache Compression in Long-Context LLMs

GRKV (Global Regression for KV Cache), a training-free KV-cache merging method that directly minimizes the discrepancy between compressed-cache and full-cache attention outputs, is proposed.

Junjie Peng, You Wu, Haoyi Wu et al. · arXiv.org · 2 citations