Cunxiao Du

According to our database, Cunxiao Du authored at least 10 papers between 2019 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.

Xuan Zhang, Cunxiao Du, Chao Du, Tianyu Pang, Wei Gao, Min Lin

CoRR, 2024

When Attention Sink Emerges in Language Models: An Empirical View.

Xiangming Gu, Tianyu Pang, Chao Du, Qian Liu, Fengzhuo Zhang, Cunxiao Du, Ye Wang, Min Lin

CoRR, 2024

Reverse Modeling in Large Language Models.

Sicheng Yu, Yuanchen Xu, Cunxiao Du, Yanying Zhou, Minghui Qiu, Qianru Sun, Hao Zhang, Jiawei Wu

CoRR, 2024

SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration.

Heming Xia, Yongqi Li, Jun Zhang, Cunxiao Du, Wenjie Li

CoRR, 2024

Efficient Inference for Large Language Model-based Generative Recommendation.

Xinyu Lin, Chaoqun Yang, Wenjie Wang, Yongqi Li, Cunxiao Du, Fuli Feng, See-Kiong Ng, Tat-Seng Chua

CoRR, 2024

GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decoding.

Cunxiao Du, Jing Jiang, Yuanchen Xu, Jiawei Wu, Sicheng Yu, Yongqi Li, Shenggui Li, Kai Xu, Liqiang Nie, Zhaopeng Tu, Yang You

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Revisiting the Markov Property for Machine Translation.

Cunxiao Du, Hao Zhou, Zhaopeng Tu, Jing Jiang

Proceedings of the Findings of the Association for Computational Linguistics: EACL 2024, 2024

2022

ngram-OAXE: Phrase-Based Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation.

Cunxiao Du, Zhaopeng Tu, Longyue Wang, Jing Jiang

Proceedings of the 29th International Conference on Computational Linguistics, 2022

2021

Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation.

Cunxiao Du, Zhaopeng Tu, Jing Jiang

Proceedings of the 38th International Conference on Machine Learning, 2021

2019

Explicit Interaction Model towards Text Classification.

Cunxiao Du, Zhaozheng Chen, Fuli Feng, Lei Zhu, Tian Gan, Liqiang Nie

Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, 2019