default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDCunxiao Du
Person information
SPARQL queries 
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
2020 – today
- 2026
[c14]Xingyao Li, Fengzhuo Zhang, Cunxiao Du, Hui Ji:
Annealed Relaxation of Speculative Decoding for Faster Autoregressive Image Generation. AAAI 2026: 23212-23220- [c13]Penghui Yang, Cunxiao Du, Fengzhuo Zhang, Haonan Wang, Tianyu Pang, Chao Du, Bo An:
LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification. ACL (1) 2026: 1826-1844 - [c12]Heming Xia, Cunxiao Du, Rui Li, Chak Tou Leong, Yongqi Li, Wenjie Li:
Merlin's Whisper: Enabling Efficient Reasoning in Large Language Models via Black-box Persuasive Prompting. ACL (1) 2026: 20021-20039 - [i21]Yuan Cheng, Fengzhuo Zhang, Yunlong Hou, Cunxiao Du, Chao Du, Tianyu Pang, Aixin Sun, Zhuoran Yang:
Demystifying the Slash Pattern in Attention: The Role of RoPE. CoRR abs/2601.08297 (2026) - [i20]Xingyao Li, Fengzhuo Zhang, Cunxiao Du, Hui Ji:
Annealed Relaxation of Speculative Decoding for Faster Autoregressive Image Generation. CoRR abs/2601.09212 (2026) - [i19]Heming Xia, Yongqi Li, Cunxiao Du, Mingbo Song, Wenjie Li:
ToolSpec: Accelerating Tool Calling via Schema-Aware and Retrieval-Augmented Speculative Decoding. CoRR abs/2604.13519 (2026) - 2025
- [j2]Haonan Wang, Qian Liu, Chao Du, Tongyao Zhu, Cunxiao Du, Kenji Kawaguchi, Tianyu Pang:
When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training. Trans. Mach. Learn. Res. 2025 (2025) - [j1]Xuan Zhang, Fengzhuo Zhang, Cunxiao Du, Chao Du, Tianyu Pang, Wei Gao, Min Lin:
LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation. Trans. Mach. Learn. Res. 2025 (2025) - [c11]Xuan Zhang, Cunxiao Du, Sicheng Yu, Jiawei Wu, Fengzhuo Zhang, Wei Gao, Qian Liu:
Sparse-to-Dense: A Free Lunch for Lossless Acceleration of Video Understanding in LLMs. ACL (2) 2025: 734-742 - [c10]Xinyu Lin, Chaoqun Yang, Wenjie Wang, Yongqi Li, Cunxiao Du, Fuli Feng, See-Kiong Ng, Tat-Seng Chua:
Efficient Inference for Large Language Model-based Generative Recommendation. ICLR 2025 - [c9]Xiangming Gu, Tianyu Pang, Chao Du, Qian Liu, Fengzhuo Zhang, Cunxiao Du, Ye Wang, Min Lin:
When Attention Sink Emerges in Language Models: An Empirical View. ICLR 2025 - [c8]Heming Xia, Yongqi Li, Jun Zhang, Cunxiao Du, Wenjie Li:
SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration. ICLR 2025 - [c7]Yunlong Hou, Fengzhuo Zhang, Cunxiao Du, Xuan Zhang, Jiachun Pan, Tianyu Pang, Chao Du, Vincent Y. F. Tan, Zhuoran Yang:
BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms. ICML 2025 - [c6]Sicheng Yu, Yuanchen Xu, Cunxiao Du, Yanying Zhou, Minghui Qiu, Qianru Sun, Hao Zhang, Jiawei Wu:
Reverse Modeling in Large Language Models. NAACL (Short Papers) 2025: 306-320 - [i18]Longxu Dou, Qian Liu, Fan Zhou, Changyu Chen, Zili Wang, Ziqi Jin, Zichen Liu, Tongyao Zhu, Cunxiao Du, Penghui Yang
, Haonan Wang, Jiaheng Liu, Yongchi Zhao, Xiachong Feng, Xin Mao, Man Tsung Yeung, Kunat Pipatanakul, Fajri Koto, Min Si Thu, Hynek Kydlícek, Zeyi Liu, Qunshu Lin, Sittipong Sripaisarnmongkol, Kridtaphad Sae-Khow, Nirattisai Thongchim, Taechawat Konkaew, Narong Borijindargoon, Anh Dao, Matichon Maneegard, Phakphum Artkaew, Zheng-Xin Yong, Quan Nguyen, Wannaphong Phatthiyaphaibun, Hoang H. Tran, Mike Zhang, Shiqi Chen, Tianyu Pang, Chao Du, Xinyi Wan, Wei Lu, Min Lin:
Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs. CoRR abs/2502.12982 (2025) - [i17]Penghui Yang, Cunxiao Du, Fengzhuo Zhang, Haonan Wang, Tianyu Pang, Chao Du, Bo An:
LongSpec: Long-Context Speculative Decoding with Efficient Drafting and Verification. CoRR abs/2502.17421 (2025) - [i16]Heming Xia, Cunxiao Du, Yongqi Li, Qian Liu, Wenjie Li:
Tutorial Proposal: Speculative Decoding for Efficient LLM Inference. CoRR abs/2503.00491 (2025) - [i15]Yunlong Hou, Fengzhuo Zhang, Cunxiao Du, Xuan Zhang, Jiachun Pan, Tianyu Pang, Chao Du, Vincent Y. F. Tan, Zhuoran Yang:
BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms. CoRR abs/2505.15141 (2025) - [i14]Xuan Zhang, Cunxiao Du, Sicheng Yu, Jiawei Wu, Fengzhuo Zhang, Wei Gao, Qian Liu:
Sparse-to-Dense: A Free Lunch for Lossless Acceleration of Video Understanding in LLMs. CoRR abs/2505.19155 (2025) - [i13]Shuche Wang, Fengzhuo Zhang, Jiaxiang Li, Cunxiao Du, Chao Du, Tianyu Pang, Zhuoran Yang, Mingyi Hong, Vincent Y. F. Tan:
Muon Outperforms Adam in Tail-End Associative Memory Learning. CoRR abs/2509.26030 (2025) - [i12]Heming Xia, Cunxiao Du, Rui Li, Chak Tou Leong, Yongqi Li, Wenjie Li:
Merlin's Whisper: Enabling Efficient Reasoning in LLMs via Black-box Adversarial Prompting. CoRR abs/2510.10528 (2025) - 2024
- [c5]Cunxiao Du, Hao Zhou, Zhaopeng Tu, Jing Jiang:
Revisiting the Markov Property for Machine Translation. EACL (Findings) 2024: 582-588 - [c4]Cunxiao Du, Jing Jiang, Yuanchen Xu, Jiawei Wu, Sicheng Yu, Yongqi Li, Shenggui Li, Kai Xu, Liqiang Nie, Zhaopeng Tu, Yang You:
GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decoding. ICML 2024: 11704-11720 - [i11]Cunxiao Du, Jing Jiang, Yuanchen Xu, Jiawei Wu, Sicheng Yu, Yongqi Li, Shenggui Li, Kai Xu, Liqiang Nie, Zhaopeng Tu, Yang You:
GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decoding. CoRR abs/2402.02082 (2024) - [i10]Cunxiao Du, Hao Zhou, Zhaopeng Tu, Jing Jiang:
Revisiting the Markov Property for Machine Translation. CoRR abs/2402.02084 (2024) - [i9]Xinyu Lin, Chaoqun Yang, Wenjie Wang, Yongqi Li, Cunxiao Du, Fuli Feng, See-Kiong Ng, Tat-Seng Chua:
Efficient Inference for Large Language Model-based Generative Recommendation. CoRR abs/2410.05165 (2024) - [i8]Heming Xia, Yongqi Li, Jun Zhang, Cunxiao Du, Wenjie Li:
SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration. CoRR abs/2410.06916 (2024) - [i7]Sicheng Yu, Yuanchen Xu, Cunxiao Du, Yanying Zhou, Minghui Qiu, Qianru Sun, Hao Zhang, Jiawei Wu:
Reverse Modeling in Large Language Models. CoRR abs/2410.09817 (2024) - [i6]Xiangming Gu, Tianyu Pang, Chao Du, Qian Liu, Fengzhuo Zhang, Cunxiao Du, Ye Wang, Min Lin:
When Attention Sink Emerges in Language Models: An Empirical View. CoRR abs/2410.10781 (2024) - [i5]Xuan Zhang, Cunxiao Du, Chao Du, Tianyu Pang, Wei Gao, Min Lin:
SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction. CoRR abs/2410.13846 (2024) - [i4]Haonan Wang, Qian Liu, Chao Du, Tongyao Zhu, Cunxiao Du, Kenji Kawaguchi, Tianyu Pang:
When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training. CoRR abs/2411.13476 (2024) - 2022
- [c3]Cunxiao Du, Zhaopeng Tu, Longyue Wang, Jing Jiang:
ngram-OAXE: Phrase-Based Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation. COLING 2022: 5035-5045 - [i3]Cunxiao Du, Zhaopeng Tu, Longyue Wang, Jing Jiang:
ngram-OAXE: Phrase-Based Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation. CoRR abs/2210.03999 (2022) - 2021
- [c2]Cunxiao Du, Zhaopeng Tu, Jing Jiang:
Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation. ICML 2021: 2849-2859 - [i2]Cunxiao Du, Zhaopeng Tu, Jing Jiang:
Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation. CoRR abs/2106.05093 (2021)
2010 – 2019
- 2019
- [c1]Cunxiao Du, Zhaozheng Chen, Fuli Feng, Lei Zhu, Tian Gan, Liqiang Nie:
Explicit Interaction Model towards Text Classification. AAAI 2019: 6359-6366 - 2018
- [i1]Cunxiao Du, Zhaozheng Chen, Fuli Feng, Lei Zhu, Tian Gan, Liqiang Nie:
Explicit Interaction Model towards Text Classification. CoRR abs/1811.09386 (2018)
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2026-07-08 01:44 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated, funded, and maintained by:
Schloss Dagstuhl - Leibniz Center for Informatics is a member of the Leibniz Association and is funded by the federal government of Germany and the states of Germany, especially Saarland and Rhineland‑Palatinate.
