Xiaocong Yang — accepted AI-conference papers

2024

Cascade Speculative Drafting for Even Faster LLM Inference

Ziyi Chen, Xiaocong Yang, Jiacheng Lin, Chenkai Sun, Kevin Chang, Jie Huang

NeurIPS 2024poster

Introduced to enhance the efficiency of large language model (LLM) inference, speculative decoding operates by having a smaller model generate a draft. A larger target model then reviews this draft to align with its output, and any acceptance by the target model results in a reduction of the number…

Cited by 39 Source ↗PDF ↗code ↗Scholar ↗

2022

NLP From Scratch Without Large-Scale Pretraining: A Simple and Efficient Framework

Xingcheng Yao, Yanan Zheng, Xiaocong Yang, Zhilin Yang

ICML 2022spotlight

Pretrained language models have become the standard approach for many NLP tasks due to strong performance, but they are very expensive to train. We propose a simple and efficient learning framework, TLM, that does not rely on large-scale pretraining. Given some labeled task data and a large general…

Cited by 58 Source ↗PDF ↗code ↗Scholar ↗