Shi-Ai Zhu

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Inference & Quantization (1)Training Efficiency & Optimization (1)

Frequent co-authors

Qi-Tong Wang (1)Xin-Wei Niu (1)Mingluo Su (1)Min Su (1)Shan-Wei Zhao (1)Huan Wang (1)

Papers (1)

Oct 8, 2026

Qi-Tong Wang +66d ago·also Westlake

SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inference

Pruning LLMs for decoding speedup is significantly improved by calibrating sparsity with actual generation activations, not just static text, and optimizing SpMV kernels.

Qi-Tong Wang, Xin-Wei Niu, Mingluo Su +4

Inference & Quantization Training Efficiency & Optimization

Shi-Ai Zhu

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)

Search

Shi-Ai Zhu

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)