logo
today local_bar

Zijia Lin

NLP expert, Kuaishou Technology

2 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 4

1 paper
Thursday, December 4, 2025 · 4:30 PM → 7:30 PM
Exhibit Hall C,D,E
PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation
#4808 · Ao Wang, Hui Chen, Jianchao Tan, Kefeng Zhang, Xunliang Cai, Zijia Lin, Jungong Han, Guiguang Ding

A kv cache compression method for large vision-language models

Poster Session 6

1 paper
Friday, December 5, 2025 · 4:30 PM → 7:30 PM
Exhibit Hall C,D,E
LongMagpie: A Self-synthesis Method for Generating Large-scale Long-context Instructions
#4007 · Chaochen Gao, Xing W, Zijia Lin, Debing Zhang, Songlin Hu