Li Wang

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)

Frequent co-authors

Yi Su (1)Xiabao Wu (1)Chiran You (1)Yongchao Liu (1)

Papers (1)

Aug 3, 2026

3w ago·also NJU

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models

Bole accelerates hybrid-attention LLMs by up to 4.72 times while slashing memory usage by up to 99 times, transforming the landscape of autoregressive decoding.

Li Wang, Yi Su, Xiabao Wu +8

Architecture Design (Transformers, SSMs, MoE)Inference & Quantization

Search

Li Wang

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)