← Authors

Canwen Xu

27 papers · 2020–2025 · 9 conferences · across top CS/AI conferences

Achievements

πŸƒ Academic Marathon (5) 🐝 Cross-Pollinator (14) πŸ—ΊοΈ Taxonomy Completionist (64) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🌈 Renaissance Researcher (5) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (9) 🀝 Dynamic Duo (17) πŸ† Grand Slam πŸ‘₯ Mega-Team (40) 🧬 Topic Evolution πŸ’Ž Century Club (27) πŸ“ˆ Trend Setter ⚑ Prolific Year (8) πŸš€ Conference Pioneer πŸ—ƒοΈ Keyword Collector (115) πŸ”₯ Unstoppable (6)

Conferences

EMNLP (9) ACL (7) NAACL (3) AAAI (2) ICLR (2) AACL (1) EACL (1) ICML (1) NIPS (1)

Top co-authors

Julian McAuley (17) Wangchunshu Zhou (7) Furu Wei (6) Tao Ge (6) Victor Sanh (4) Ke Xu (4) Han Wang (3) Daya Guo (3) Nan Duan (3) Gunjan Chhablani (3)

Research topics

Resources & Methods (1)

Keywords

self-supervised learning (4) model compression (4) text classification (4) transfer learning (3) pretrained language model (3) knowledge distillation (3) large language model (3) question answering (3) natural language processing (3) few-shot learning (2) early exit (2) language model (2) text generation (2) direct preference optimization (2) semantic analysis (2) parameter-efficient tuning (2) preference learning (1) code completion (1) contrastive learning (1) representation learning (1)

Papers

Optimizing Reasoning for Text-to-SQL with Execution Feedback ACL 2025
Small Models are Valuable Plug-ins for Large Language Models ACL 2024
Automatic Pair Construction for Contrastive Post-training NAACL 2024
RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems ICLR 2024
Baize: An Open-Source Chat Model with Parameter-Efficient Tuning on Self-Chat Data EMNLP 2023
LongCoder: A Long-Range Pre-trained Language Model for Code Completion ICML 2023
A Survey on Dynamic Neural Networks for Natural Language Processing EACL 2023
A Survey on Model Compression and Acceleration for Pretrained Language Models AAAI 2023
Spoiler Detection as Semantic Text Matching EMNLP 2023
Automatic Multi-Label Prompting: Simple and Interpretable Few-Shot Classification NAACL 2022
Efficiently Tuned Parameters Are Task Embeddings EMNLP 2022
BERT Learns to Teach: Knowledge Distillation with Meta Learning ACL 2022
PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts ACL 2022
LaPraDoR: Unsupervised Pretrained Dense Retriever for Zero-Shot Text Retrieval ACL 2022
InforMask: Unsupervised Informative Masking for Language Model Pretraining EMNLP 2022
Multitask Prompted Training Enables Zero-Shot Task Generalization ICLR 2022
Leashing the Inner Demons: Self-Detoxification for Language Models AAAI 2022
Blow the Dog Whistle: A Chinese Dataset for Cant Understanding with Common Sense and World Knowledge NAACL 2021
Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting EMNLP 2021
Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT Compression EMNLP 2021
Datasets: A Community Library for Natural Language Processing EMNLP 2021
Transformers: State-of-the-Art Natural Language Processing EMNLP 2020
UnihanLM: Coarse-to-Fine Chinese-Japanese Language Model Pretraining with the Unihan Database AACL 2020
Pre-train and Plug-in: Flexible Conditional Text Generation with Variational Auto-Encoders ACL 2020
MATINF: A Jointly Labeled Large-Scale Dataset for Classification, Question Answering and Summarization ACL 2020
BERT-of-Theseus: Compressing BERT by Progressive Module Replacing EMNLP 2020
BERT Loses Patience: Fast and Robust Inference with Early Exit NIPS 2020