publications
publications by categories in reversed chronological order. generated by jekyll-scholar.
2025
-  arXiv
 -  NeurIPSEfficient Speech Language Modeling via Energy Distance in Continuous Latent SpaceIn Neural Information Processing Systems, 2025
 -  ICMLContinuous Visual Autoregressive Generation via Score MaximizationIn International Conference on Machine Learning, 2025
 -  ICLRPatch-Level Training for Large Language ModelsIn International Conference on Learning Representations, 2025
 
2024
-  ACLUnderstanding and Addressing the Under-Translation Problem from the Perspective of Decoding Objective2024
 -  ICMLLanguage generation with strictly proper scoring rulesIn International Conference on Machine Learning, 2024
 -  ACL FindingsInstruction position matters in sequence generation with large language modelsIn Findings of Association for Computational Linguistics, 2024
 
2023
-  NeurIPSNon-autoregressive machine translation with probabilistic context-free grammarIn Neural Information Processing Systems, 2023
 -  EMNLPNon-autoregressive streaming transformer for simultaneous translationIn Empirical Methods in Natural Language Processing, 2023
 -  NeurIPS
 -  AAAIRephrasing the reference for non-autoregressive machine translationIn AAAI Conference on Artificial Intelligence, 2023
 -  ICLRFuzzy alignments in directed acyclic graph for non-autoregressive machine translationIn International Conference on Learning Representations, 2023
 
2022
-  EMNLP FindingsViterbi decoding of directed acyclic transformer for non-autoregressive machine translationIn Findings of Empirical Methods in Natural Language Processing, 2022
 -  NeurIPSNon-Monotonic Latent Alignments for CTC-Based Non-Autoregressive Machine TranslationIn Neural Information Processing Systems, 2022
 -  NAACLOne reference is not enough: Diverse distillation with reference selection for non-autoregressive translationIn North American Chapter of the Association for Computational Linguistics, 2022
 -  ACLOvercoming catastrophic forgetting beyond continual learning: Balanced training for neural machine translationIn Association for Computational Linguistics, 2022
 
2021
-  CLSequence-level Training for Non-autoregressive Neural Machine TranslationIn Computational Linguistics, 2021
 -  ACLGuiding teacher forcing with seer forcing for neural machine translationIn Association for Computational Linguistics, 2021
 
2020
-  EMNLPGenerating diverse translation from model distribution with dropoutIn Empirical Methods in Natural Language Processing, 2020
 
2019
-  AAAIModeling Fluency and Faithfulness for Diverse Neural Machine TranslationIn AAAI Conference on Artificial Intelligence, 2019
 -  AAAIMinimizing the Bag-of-Ngrams Difference for Non-Autoregressive Neural Machine TranslationIn AAAI Conference on Artificial Intelligence, 2019
 -  ACLRetrieving sequential information for non-autoregressive neural machine translationIn Association for Computational Linguistics, 2019
 
2018
-  EMNLPGreedy search with probabilistic n-gram matching for neural machine translationIn Empirical Methods in Natural Language Processing, 2018