Wenjie Pei

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Architecture Design (Transformers, SSMs, MoE) (1)Inference & Quantization (1)Training Efficiency & Optimization (1)

Frequent co-authors

Yufei Xu (1)Fanxu Meng (1)Fan Jiang (1)YuXuan Wang (1)

Papers (1)

Mar 30, 2026

Yufei Xu +142d ago

HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention

Scanning every token to focus attention is now passé: HISA prunes irrelevant context blocks *before* token-level scoring, slashing compute without sacrificing selection fidelity.

Yufei Xu, Fanxu Meng, Fan Jiang +12

Architecture Design (Transformers, SSMs, MoE)Inference & Quantization Training Efficiency & Optimization

Search

Wenjie Pei

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)