Xiaofei Ma

51 papers A* 4Journal 30Unranked 17
YearRankTypeTitle / Venue / Authors
2025 — conf
LibEvolutionEval: A Benchmark and Study for Version-Specific Code Generation.
NAACL (Long Papers)
Sachit Kuhar, Wasi Uddin Ahmad, Zijian Wang, Nihal Jain, Haifeng Qian, Baishakhi Ray, Murali Krishna Ramanathan, Xiaofei Ma, Anoop Deoras
2025 J jnl
Structural Code Search using Natural Language Queries.
CoRR
Ben Limpanukorn, Yanjun Wang, Zach Patterson, Pranav Garg, Murali Krishna Ramanathan, Xiaofei Ma, Anoop Deoras, Miryung Kim
2025 J jnl
UTFix: Change Aware Unit Test Repairing using LLM.
CoRR
Shanto Rahman, Sachit Kuhar, Berk Çirisci, Pranav Garg, Shiqi Wang, Xiaofei Ma, Anoop Deoras, Baishakhi Ray
2025 J jnl
UTFix: Change Aware Unit Test Repairing using LLM.
Proc. ACM Program. Lang.
Shanto Rahman, Sachit Kuhar, Berk Çirisci, Pranav Garg, Shiqi Wang, Xiaofei Ma, Anoop Deoras, Baishakhi Ray
2024 J jnl
Approximately Aligned Decoding.
CoRR
Daniel Melcer, Sujan K. Gonugondla, Pramuditha Perera, Haifeng Qian, Wen-Hao Chiang, Yanjun Wang, Nihal Jain, Pranav Garg, Xiaofei Ma, Anoop Deoras
2024 — conf
BASS: Batched Attention-optimized Speculative Sampling.
ACL (Findings)
Haifeng Qian, Sujan Kumar Gonugondla, Sungsoo Ha, Mingyue Shang, Sanjay Krishna Gouda, Ramesh Nallapati, Sudipta Sengupta, Xiaofei Ma, Anoop Deoras
2024 J jnl
BASS: Batched Attention-optimized Speculative Sampling.
CoRR
Haifeng Qian, Sujan Kumar Gonugondla, Sungsoo Ha, Mingyue Shang, Sanjay Krishna Gouda, Ramesh Nallapati, Sudipta Sengupta, Xiaofei Ma, Anoop Deoras
2024 J jnl
Code Representation Learning At Scale.
CoRR
Dejiao Zhang, Wasi Uddin Ahmad, Ming Tan, Hantian Ding, Ramesh Nallapati, Dan Roth, Xiaofei Ma, Bing Xiang
2024 A* conf
Code Representation Learning at Scale.
ICLR
Dejiao Zhang, Wasi Uddin Ahmad, Ming Tan, Hantian Ding, Ramesh Nallapati, Dan Roth, Xiaofei Ma, Bing Xiang
2024 J jnl
Code-Aware Prompting: A Study of Coverage-Guided Test Generation in Regression Setting using LLM.
Proc. ACM Softw. Eng.
Gabriel Ryan, Siddhartha Jain, Mingyue Shang, Shiqi Wang, Xiaofei Ma, Murali Krishna Ramanathan, Baishakhi Ray
2024 J jnl
Code-Aware Prompting: A study of Coverage Guided Test Generation in Regression Setting using LLM.
CoRR
Gabriel Ryan, Siddhartha Jain, Mingyue Shang, Shiqi Wang, Xiaofei Ma, Murali Krishna Ramanathan, Baishakhi Ray
2024 — conf
CodeFort: Robust Training for Code Generation Models.
EMNLP (Findings)
Yuhao Zhang, Shiqi Wang, Haifeng Qian, Zijian Wang, Mingyue Shang, Linbo Liu, Sanjay Krishna Gouda, Baishakhi Ray, Murali Krishna Ramanathan, Xiaofei Ma, Anoop Deoras
2024 J jnl
CodeFort: Robust Training for Code Generation Models.
CoRR
Yuhao Zhang, Shiqi Wang, Haifeng Qian, Zijian Wang, Mingyue Shang, Linbo Liu, Sanjay Krishna Gouda, Baishakhi Ray, Murali Krishna Ramanathan, Xiaofei Ma, Anoop Deoras
2024 A* conf
LeDex: Training LLMs to Better Self-Debug and Explain Code.
NeurIPS
Nan Jiang, Xiaopeng Li, Shiqi Wang, Qiang Zhou, Soneya Binta Hossain, Baishakhi Ray, Varun Kumar, Xiaofei Ma, Anoop Deoras
2024 J jnl
LibEvolutionEval: A Benchmark and Study for Version-Specific Code Generation.
CoRR
Sachit Kuhar, Wasi Uddin Ahmad, Zijian Wang, Nihal Jain, Haifeng Qian, Baishakhi Ray, Murali Krishna Ramanathan, Xiaofei Ma, Anoop Deoras
2024 — conf
Lightweight reranking for language model generations.
ACL (1)
Siddhartha Jain, Xiaofei Ma, Anoop Deoras, Bing Xiang
2024 A* conf
Repoformer: Selective Retrieval for Repository-Level Code Completion.
ICML
Di Wu, Wasi Uddin Ahmad, Dejiao Zhang, Murali Krishna Ramanathan, Xiaofei Ma
2024 J jnl
Repoformer: Selective Retrieval for Repository-Level Code Completion.
CoRR
Di Wu, Wasi Uddin Ahmad, Dejiao Zhang, Murali Krishna Ramanathan, Xiaofei Ma
2024 J jnl
Training LLMs to Better Self-Debug and Explain Code.
CoRR
Nan Jiang, Xiaopeng Li, Shiqi Wang, Qiang Zhou, Soneya Binta Hossain, Baishakhi Ray, Varun Kumar, Xiaofei Ma, Anoop Deoras
2023 — conf
ContraCLM: Contrastive Learning For Causal Language Model.
ACL (1)
Nihal Jain, Dejiao Zhang, Wasi Uddin Ahmad, Zijian Wang, Feng Nan, Xiaopeng Li, Ming Tan, Ramesh Nallapati, Baishakhi Ray, Parminder Bhatia, Xiaofei Ma, Bing Xiang
2023 — conf
Efficient Shapley Values Estimation by Amortization for Text Classification.
ACL (1)
Chenghao Yang, Fan Yin, He He, Kai-Wei Chang, Xiaofei Ma, Bing Xiang
2023 J jnl
Efficient Shapley Values Estimation by Amortization for Text Classification.
CoRR
Chenghao Yang, Fan Yin, He He, Kai-Wei Chang, Xiaofei Ma, Bing Xiang
2023 — conf
Exploring Continual Learning for Code Generation Models.
ACL (2)
Prateek Yadav, Qing Sun, Hantian Ding, Xiaopeng Li, Dejiao Zhang, Ming Tan, Parminder Bhatia, Xiaofei Ma, Ramesh Nallapati, Murali Krishna Ramanathan, Mohit Bansal, Bing Xiang
2023 J jnl
Exploring Continual Learning for Code Generation Models.
CoRR
Prateek Yadav, Qing Sun, Hantian Ding, Xiaopeng Li, Dejiao Zhang, Ming Tan, Xiaofei Ma, Parminder Bhatia, Ramesh Nallapati, Murali Krishna Ramanathan, Mohit Bansal, Bing Xiang
2023 — conf
Multitask Pretraining with Structured Knowledge for Text-to-SQL Generation.
ACL (1)
Robert Giaquinto, Dejiao Zhang, Benjamin Kleiner, Yang Li, Ming Tan, Parminder Bhatia, Ramesh Nallapati, Xiaofei Ma
2023 A* conf
STREET: A Multi-Task Structured Reasoning and Explanation Benchmark.
ICLR
Danilo Neves Ribeiro, Shen Wang, Xiaofei Ma, Henghui Zhu, Rui Dong, Deguang Kong, Juliette Burger, Anjelica Ramos, Zhiheng Huang, William Yang Wang, George Karypis, Bing Xiang, Dan Roth
2023 J jnl
STREET: A Multi-Task Structured Reasoning and Explanation Benchmark.
CoRR
Danilo Neves Ribeiro, Shen Wang, Xiaofei Ma, Henry Zhu, Rui Dong, Deguang Kong, Juliette Burger, Anjelica Ramos, William Yang Wang, Zhiheng Huang, George Karypis, Bing Xiang, Dan Roth
2023 — conf
SWING: Balancing Coverage and Faithfulness for Dialogue Summarization.
EACL (Findings)
Kung-Hsiang Huang, Siffi Singh, Xiaofei Ma, Wei Xiao, Feng Nan, Nicholas Dingwall, William Yang Wang, Kathleen R. McKeown
2023 J jnl
SWING: Balancing Coverage and Faithfulness for Dialogue Summarization.
CoRR
Kung-Hsiang Huang, Siffi Singh, Xiaofei Ma, Wei Xiao, Feng Nan, Nicholas Dingwall, William Yang Wang, Kathleen R. McKeown
2023 J jnl
Self-consistency for open-ended generations.
CoRR
Siddhartha Jain, Xiaofei Ma, Anoop Deoras, Bing Xiang
2022 J jnl
ContraGen: Effective Contrastive Learning For Causal Language Model.
CoRR
Nihal Jain, Dejiao Zhang, Wasi Uddin Ahmad, Zijian Wang, Feng Nan, Xiaopeng Li, Ming Tan, Ramesh Nallapati, Baishakhi Ray, Parminder Bhatia, Xiaofei Ma, Bing Xiang
2022 J jnl
Debiasing Neural Retrieval via In-batch Balancing Regularization.
CoRR
Yuantong Li, Xiaokai Wei, Zijian Wang, Shen Wang, Parminder Bhatia, Xiaofei Ma, Andrew O. Arnold
2022 — conf
Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner.
NAACL-HLT (Findings)
Danilo Neves Ribeiro, Shen Wang, Xiaofei Ma, Rui Dong, Xiaokai Wei, Henghui Zhu, Xinchi Chen, Peng Xu, Zhiheng Huang, Andrew O. Arnold, Dan Roth
2022 J jnl
Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner.
CoRR
Danilo Neves Ribeiro, Shen Wang, Xiaofei Ma, Rui Dong, Xiaokai Wei, Henry Zhu, Xinchi Chen, Zhiheng Huang, Peng Xu, Andrew O. Arnold, Dan Roth
2022 — conf
Learning Dialogue Representations from Consecutive Utterances.
NAACL-HLT
Zhihan Zhou, Dejiao Zhang, Wei Xiao, Nicholas Dingwall, Xiaofei Ma, Andrew O. Arnold, Bing Xiang
2022 J jnl
Learning Dialogue Representations from Consecutive Utterances.
CoRR
Zhihan Zhou, Dejiao Zhang, Wei Xiao, Nicholas Dingwall, Xiaofei Ma, Andrew O. Arnold, Bing Xiang
2022 J jnl
Uncertainty-Based Active Learning for Reading Comprehension.
Trans. Mach. Learn. Res.
Jing Wang, Jie Shen, Xiaofei Ma, Andrew O. Arnold
2022 — conf
Virtual Augmentation Supported Contrastive Learning of Sentence Representations.
ACL (Findings)
Dejiao Zhang, Wei Xiao, Henghui Zhu, Xiaofei Ma, Andrew O. Arnold
2021 — conf
Contrastive Document Representation Learning with Graph Attention Networks.
EMNLP (Findings)
Peng Xu, Xinchi Chen, Xiaofei Ma, Zhiheng Huang, Bing Xiang
2021 J jnl
Contrastive Document Representation Learning with Graph Attention Networks.
CoRR
Peng Xu, Xinchi Chen, Xiaofei Ma, Zhiheng Huang, Bing Xiang
2021 — conf
Contrastive Fine-tuning Improves Robustness for Neural Rankers.
ACL/IJCNLP (Findings)
Xiaofei Ma, Cícero Nogueira dos Santos, Andrew O. Arnold
2021 J jnl
Contrastive Fine-tuning Improves Robustness for Neural Rankers.
CoRR
Xiaofei Ma, Cícero Nogueira dos Santos, Andrew O. Arnold
2021 J jnl
Robust Information Retrieval for False Claims with Distracting Entities In Fact Extraction and Verification.
CoRR
Mingwen Dong, Christos Christodoulopoulos, Sheng-Min Shih, Xiaofei Ma
2021 J jnl
Virtual Augmentation Supported Contrastive Learning of Sentence Representations.
CoRR
Dejiao Zhang, Wei Xiao, Henghui Zhu, Xiaofei Ma, Andrew O. Arnold
2020 — conf
Beyond [CLS] through Ranking by Generation.
EMNLP (1)
Cícero Nogueira dos Santos, Xiaofei Ma, Ramesh Nallapati, Zhiheng Huang, Bing Xiang
2020 J jnl
Beyond [CLS] through Ranking by Generation.
CoRR
Cícero Nogueira dos Santos, Xiaofei Ma, Ramesh Nallapati, Zhiheng Huang, Bing Xiang
2019 — conf
Domain Adaptation with BERT-based Domain Classification and Data Selection.
DeepLo@EMNLP-IJCNLP
Xiaofei Ma, Peng Xu, Zhiguo Wang, Ramesh Nallapati, Bing Xiang
2019 — conf
Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering.
EMNLP/IJCNLP (1)
Zhiguo Wang, Patrick Ng, Xiaofei Ma, Ramesh Nallapati, Bing Xiang
2019 J jnl
Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering.
CoRR
Zhiguo Wang, Patrick Ng, Xiaofei Ma, Ramesh Nallapati, Bing Xiang
2019 J jnl
Passage Ranking with Weak Supervsion.
CoRR
Peng Xu, Xiaofei Ma, Ramesh Nallapati, Bing Xiang
2019 J jnl
Universal Text Representation from BERT: An Empirical Study.
CoRR
Xiaofei Ma, Zhiguo Wang, Patrick Ng, Ramesh Nallapati, Bing Xiang