← Search

Wenhao Lu

2 accepted papers

2025

QSpec: Speculative Decoding with Complementary Quantization Schemes

EMNLP 2025

Quantization is widely adopted to accelerate inference and reduce memory consumption in large language models (LLMs). While activation-weight joint quantization enables efficient low-precision decoding, it suffers substantial performance degradation on multi-step reasoning tasks. We propose QSPEC, a

2024

Enhancing Zero-Shot Chain-of-Thought Reasoning in Large Language Models through Logic

COLING 2024main

Recent advancements in large language models have showcased their remarkable generalizability across various domains. However, their reasoning abilities still have significant room for improvement, especially when confronted with scenarios requiring multi-step reasoning. Although large language mode…