עקוב אחר
Cunxiao Du
Cunxiao Du
Research Scientist at Sea AI Lab
כתובת אימייל מאומתת בדומיין phdis.smu.edu.sg - דף הבית
כותרת
צוטט על ידי
צוטט על ידי
שנה
Explicit interaction model towards text classification‏
C Du, Z Chen, F Feng, L Zhu, T Gan, L Nie‏
AAAI, 2019‏
1332019
Order-agnostic cross entropy for non-autoregressive machine translation‏
C Du, Z Tu, J Jiang‏
ICML, 2021‏
862021
Glide with a cape: A low-hassle method to accelerate speculative decoding‏
C Du, J Jiang, X Yuanchen, J Wu, S Yu, Y Li, S Li, K Xu, L Nie, Z Tu, ...‏
ICML, 2024‏
112024
ngram-OAXE: Phrase-Based Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation‏
C Du, Z Tu, L Wang, J Jiang‏
COLING 2022, 2022‏
112022
Simlayerkv: A simple framework for layer-level KV cache reduction‏
X Zhang, C Du, C Du, T Pang, W Gao, M Lin‏
arXiv preprint arXiv:2410.13846, 2024‏
32024
When Attention Sink Emerges in Language Models: An Empirical View‏
X Gu, T Pang, C Du, Q Liu, F Zhang, C Du, Y Wang, M Lin‏
arXiv preprint arXiv:2410.10781, 2024‏
22024
When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training‏
H Wang, Q Liu, C Du, T Zhu, C Du, K Kawaguchi, T Pang‏
arXiv preprint arXiv:2411.13476, 2024‏
12024
Efficient Inference for Large Language Model-based Generative Recommendation‏
X Lin, C Yang, W Wang, Y Li, C Du, F Feng, SK Ng, TS Chua‏
arXiv preprint arXiv:2410.05165, 2024‏
12024
Revisiting the Markov Property for Machine Translation‏
C Du, H Zhou, Z Tu, J Jiang‏
Findings of EACL, 2024‏
12024
LongSpec: Long-Context Speculative Decoding with Efficient Drafting and Verification‏
P Yang, C Du, F Zhang, H Wang, T Pang, C Du, B An‏
arXiv preprint arXiv:2502.17421, 2025‏
2025
Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs‏
L Dou, Q Liu, F Zhou, C Chen, Z Wang, Z Jin, Z Liu, T Zhu, C Du, P Yang, ...‏
arXiv preprint arXiv:2502.12982, 2025‏
2025
Reverse Modeling in Large Language Models‏
S Yu, Y Xu, C Du, Y Zhou, M Qiu, Q Sun, H Zhang, J Wu‏
arXiv preprint arXiv:2410.09817, 2024‏
2024
SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration‏
H Xia, Y Li, J Zhang, C Du, W Li‏
arXiv preprint arXiv:2410.06916, 2024‏
2024
Towards faster inference of transformers: Strategies for accelerating decoding processes‏
C DU‏
Singapore Management University, 2024‏
2024
המערכת אינה יכולה לבצע את הפעולה כעת. נסה שוב מאוחר יותר.
מאמרים 1–14