Canwen Xu

10.8k citations

20 papers · 761 indexed · 1 hit paper · h-index 9

Artificial Intelligence top 2%
Computer Vision and Pattern Recognition top 5%
Information Systems top 10%
Sociology and Political Science
Molecular Biology

Co-authors: Julian McAuley Wangchunshu Zhou Thomas WolfQuentin LhoestJulien Plu Yacine Jernite Alexander M. RushAnthony Moi
Topics: Topic Modeling (14 papers)Natural Language Processing Techniques (10 papers)Multimodal Machine Learning Applications (7 papers)
Cited by: Artificial Intelligence Computer Vision and Pattern Recognition Health Informatics
Journals: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)Proceedings of the 2021 Conference on Empirical Methods in Natural Language ProcessingProceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Partner nations: United States China Switzerland

In The Last Decade

Canwen Xu

19 papers receiving 693 citations

Hit Papers

align trajectories

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the same subfield and year (this is the minimum needed to enter the top 1%, not the average within it), or reaches the top citation threshold in at least one of its specific research topics.

Transformers: State-of-the-Art Natural Language Processing

2020 436 citations Thomas Wolf, Lysandre Debut et al. Zenodo (CERN European Organization for Nuclear Research) profile →

Peers

Countries citing papers authored by Canwen Xu

Since Specialization

Citations

This map shows the geographic impact of Canwen Xu's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Canwen Xu with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Canwen Xu more than expected).

Fields of papers citing papers by Canwen Xu

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Canwen Xu. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Canwen Xu. The network helps show where Canwen Xu may publish in the future.

Co-authorship network of co-authors of Canwen Xu

This figure shows the co-authorship network connecting the top 25 collaborators of Canwen Xu. A scholar is included among the top collaborators of Canwen Xu based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Canwen Xu. Canwen Xu is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

Sort: Min cites: Since: Top N: Style:

20 of 20 papers shown

#	Work	Indexed citations
1	Optimizing Reasoning for Text-to-SQL with Execution Feedback 2025 ·(unknown),Canwen Xu,Yuxiong He,Zhewei Yao	0
2	Small Models are Valuable Plug-ins for Large Language Models 2024 ·Canwen Xu,Xu Yi‐chong,Shuohang Wang,Yang Liu,(unknown),Julian McAuley	18
3	Baize: An Open-Source Chat Model with Parameter-Efficient Tuning on Self-Chat Data 2023 ·Canwen Xu,Daya Guo,Nan Duan,Julian McAuley	59
4	A Survey on Model Compression and Acceleration for Pretrained Language Models 2023 ·Proceedings of the AAAI Conference on Artificial Intelligence ·Canwen Xu,Julian McAuley	25
5	Spoiler Detection as Semantic Text Matching 2023 ·(unknown),Canwen Xu,Julian McAuley	1
6	A Survey on Dynamic Neural Networks for Natural Language Processing 2023 ·Canwen Xu,Julian McAuley	4
7	InforMask: Unsupervised Informative Masking for Language Model Pretraining 2022 ·(unknown),Canwen Xu,Julian McAuley	5
8	LaPraDoR: Unsupervised Pretrained Dense Retriever for Zero-Shot Text Retrieval 2022 ·Findings of the Association for Computational Linguistics: ACL 2022 ·Canwen Xu,Daya Guo,Nan Duan,Julian McAuley	14
9	BERT Learns to Teach: Knowledge Distillation with Meta Learning 2022 ·Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) ·Wangchunshu Zhou,Canwen Xu,Julian McAuley	36
10	Efficiently Tuned Parameters Are Task Embeddings 2022 ·Wangchunshu Zhou,Canwen Xu,Julian McAuley	1
11	Leashing the Inner Demons: Self-Detoxification for Language Models 2022 ·Proceedings of the AAAI Conference on Artificial Intelligence ·Canwen Xu,Zexue He,Zhankui He,Julian McAuley	11
12	Automatic Multi-Label Prompting: Simple and Interpretable Few-Shot Classification 2022 ·Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies ·Han Wang,Canwen Xu,Julian McAuley	8
13	Blow the Dog Whistle: A Chinese Dataset for Cant Understanding with Common Sense and World Knowledge 2021 ·Canwen Xu,Wangchunshu Zhou,Tao Ge,Ke Xu,Julian McAuley,Furu Wei	7
14	Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting 2021 ·Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing ·Wangchunshu Zhou,Tao Ge,Canwen Xu,Ke Xu,Furu Wei	5
15	Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT Compression 2021 ·Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing ·Canwen Xu,Wangchunshu Zhou,Tao Ge,Ke Xu,Julian McAuley,Furu Wei	19
16	BERT-of-Theseus: Compressing BERT by Progressive Module Replacing 2020 ·Canwen Xu,Wangchunshu Zhou,Tao Ge,Furu Wei,Ming Zhou	100
17	UnihanLM: Coarse-to-Fine Chinese-Japanese Language Model Pretraining with the Unihan Database 2020 ·Canwen Xu,Tao Ge,Chenliang Li,Furu Wei	2
18	MATINF: A Jointly Labeled Large-Scale Dataset for Classification, Question Answering and Summarization 2020 ·Canwen Xu,(unknown),(unknown),(unknown),Chenliang Li	7
19	Transformers: State-of-the-Art Natural Language Processingbreakdown → 2020 ·Zenodo (CERN European Organization for Nuclear Research) ·Thomas Wolf,Lysandre Debut,Victor Sanh,Julien Chaumond,Clément Delangue,Anthony Moi,(unknown),(unknown),Yacine Jernite,Julien Plu,Canwen Xu,Teven Le Scao,Sylvain Gugger,(unknown),Quentin Lhoest,Alexander M. Rush	436
20	Parallel Association Rule Mining for Medical Applications 2011 ·(unknown),Canwen Xu,Phillip C.‐Y. Sheu,Hiroshi Yamaguchi	3

About Canwen Xu

Canwen Xu is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition and General Social Sciences, having authored 20 papers that have together received 761 indexed citations. Recurring topics across this work include Topic Modeling (14 papers), Natural Language Processing Techniques (10 papers) and Multimodal Machine Learning Applications (7 papers). The work is most often cited by research in Artificial Intelligence (691 citations), Computer Vision and Pattern Recognition (193 citations) and Health Informatics (11 citations). Canwen Xu has collaborated with scholars based in United States, China and Switzerland. Frequent co-authors include Julian McAuley, Wangchunshu Zhou, Thomas Wolf, Quentin Lhoest, Julien Plu, Yacine Jernite, Alexander M. Rush, Anthony Moi, Julien Chaumond and Lysandre Debut. Their work appears in journals such as Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing and Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact