SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration von Xia, Heming, Li, Yongqi, Zhang, Jun, Du, Cunxiao, Li, Wenjie

Volltext bestellen

Revisiting the Markov Property for Machine Translation von Du, Cunxiao, Zhou, Hao, Tu, Zhaopeng, Jiang, Jing

Volltext bestellen

When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training von Wang, Haonan, Liu, Qian, Du, Chao, Zhu, Tongyao, Du, Cunxiao, Kawaguchi, Kenji, Pang, Tianyu

Volltext bestellen

SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction von Zhang, Xuan, Du, Cunxiao, Du, Chao, Pang, Tianyu, Gao, Wei, Lin, Min

Volltext bestellen

When Attention Sink Emerges in Language Models: An Empirical View von Gu, Xiangming, Pang, Tianyu, Du, Chao, Liu, Qian, Zhang, Fengzhuo, Du, Cunxiao, Wang, Ye, Lin, Min

Volltext bestellen

Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation von Du, Cunxiao, Tu, Zhaopeng, Jiang, Jing

Volltext bestellen

Reverse Modeling in Large Language Models von Yu, Sicheng, Xu, Yuanchen, Du, Cunxiao, Zhou, Yanying, Qiu, Minghui, Sun, Qianru, Zhang, Hao, Wu, Jiawei

Volltext bestellen

ngram-OAXE: Phrase-Based Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation von Du, Cunxiao, Tu, Zhaopeng, Wang, Longyue, Jiang, Jing

Volltext bestellen

Efficient Inference for Large Language Model-based Generative Recommendation von Lin, Xinyu, Yang, Chaoqun, Wang, Wenjie, Li, Yongqi, Du, Cunxiao, Feng, Fuli, Ng, See-Kiong, Chua, Tat-Seng

Volltext bestellen

SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration von Xia, Heming, Li, Yongqi, Zhang, Jun, Du, Cunxiao, Li, Wenjie

Volltext

GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decoding von Du, Cunxiao, Jiang, Jing, Yuanchen, Xu, Wu, Jiawei, Yu, Sicheng, Li, Yongqi, Li, Shenggui, Xu, Kai, Nie, Liqiang, Tu, Zhaopeng, You, Yang

Volltext bestellen

Revisiting the Markov Property for Machine Translation von Du, Cunxiao, Zhou, Hao, Tu, Zhaopeng, Jiang, Jing

Volltext

When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training von Wang, Haonan, Liu, Qian, Du, Chao, Zhu, Tongyao, Du, Cunxiao, Kawaguchi, Kenji, Pang, Tianyu

Volltext

SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction von Zhang, Xuan, Du, Cunxiao, Du, Chao, Pang, Tianyu, Gao, Wei, Lin, Min

Volltext

When Attention Sink Emerges in Language Models: An Empirical View von Gu, Xiangming, Pang, Tianyu, Du, Chao, Liu, Qian, Zhang, Fengzhuo, Du, Cunxiao, Wang, Ye, Lin, Min

Volltext

Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation von Du, Cunxiao, Tu, Zhaopeng, Jiang, Jing

Volltext

Reverse Modeling in Large Language Models von Yu, Sicheng, Xu, Yuanchen, Du, Cunxiao, Zhou, Yanying, Qiu, Minghui, Sun, Qianru, Zhang, Hao, Wu, Jiawei

Volltext

ngram-OAXE: Phrase-Based Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation von Du, Cunxiao, Tu, Zhaopeng, Wang, Longyue, Jiang, Jing

Volltext

Efficient Inference for Large Language Model-based Generative Recommendation von Lin, Xinyu, Yang, Chaoqun, Wang, Wenjie, Li, Yongqi, Du, Cunxiao, Feng, Fuli, See-Kiong Ng, Tat-Seng Chua

Volltext

Explicit Interaction Model towards Text Classification von Du, Cunxiao, Chin, Zhaozheng, Feng, Fuli, Zhu, Lei, Gan, Tian, Nie, Liqiang

Volltext bestellen