Showing cs.CLShow all
3 papers · 1 filter
cs.CL2026
POP: Prefill-Only Pruning for Efficient Large Model Inference
Junhui He, Zhihui Fu, Jun Wang +1
Large Language Models (LLMs) and Vision-Language Models (VLMs) have demonstrated remarkable capabilities. However, their deployment is hindered by significant computational costs.…
cs.CL2025
When, What, and How: Rethinking Retrieval-Enhanced Speculative Decoding
Min Fang, Zhihui Fu, Qibin Zhao +1
Speculative decoding (SD) has emerged as an effective technique to accelerate large language model (LLM) inference without compromising output quality. However, the achievable spee…
cs.CL2025
DiffuSpec: Unlocking Diffusion Language Models for Speculative Decoding
Guanghao Li, Zhihui Fu, Min Fang +4
As large language models (LLMs) scale up, accuracy improves, but the autoregressive (AR) nature of decoding increases latency since each token requires a serial forward pass. Specu…