today local_bar

Haiyuan Wan

PhD student, Tsinghua University

1 paper at NeurIPS 2025

OpenReview· Semantic Scholar· Google Scholar

Poster Session 5

Friday, December 5, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

Spotlight Attention: Towards Efficient LLM Generation via Non-linear Hashing-based KV Cache Retrieval

#5514 · Wenhao Li, Yuxin Zhang, Gen Luo, Haiyuan Wan, ZiYang Gong, Fei Chao, Rongrong Ji

KV cache retrieval for large language models using nonlinear hashing function.