Mingxuan Wang

MessToClean: Evidence-Grounded Structure-Preserving Reconstruction for Real-World Degraded Exam Paper Images ACL 2026 Both Text and Images Leaked! A Systematic Analysis of Data Contamination in Multimodal LLM EMNLP 2025 Empowering Self-Learning of LLMs: Inner Knowledge Explicitation as a Catalyst AAAI 2025 Diffusion Glancing Transformer for Parallel Sequence-to-Sequence Learning NAACL 2024 PolyVoice: Language Models for Speech to Speech Translation ICLR 2024 Only 5% Attention Is All You Need: Efficient Long-range Document-level Neural Machine Translation IJCNLP 2023 Recent Advances in Direct Speech-to-text Translation IJCAI 2023 Leveraging per Image-Token Consistency for Vision-Language Pre-Training CVPR 2023 Only 5% Attention Is All You Need: Efficient Long-range Document-level Neural Machine Translation AACL 2023 MobileNMT: Enabling Translation in 15MB and 30ms ACL 2023 Beyond Triplet: Leveraging the Most Data for Multimodal Machine Translation ACL 2023 DUB: Discrete Unit Back-translation for Speech Translation ACL 2023 BigVideo: A Large-scale Video Subtitle Translation Dataset for Multimodal Machine Translation ACL 2023 FINDINGS OF THE IWSLT 2023 EVALUATION CAMPAIGN ACL 2023 CoBERT: Self-Supervised Speech Representation Learning Through Code Representation Learning INTERSPEECH 2023 GigaST: A 10,000-hour Pseudo Speech Translation Corpus INTERSPEECH 2023 SESCORE2: Learning Text Generation Evaluation via Synthesizing Realistic Mistakes ACL 2023 BLEURT Has Universal Translations: An Analysis of Automatic Metrics by Minimum Risk Training ACL 2023 CTC-based Non-autoregressive Speech Translation ACL 2023 MOSPC: MOS Prediction Based on Pairwise Comparison ACL 2023 Controlling Styles in Neural Machine Translation with Activation Prompt ACL 2023 The VolcTrans System for WMT22 Multilingual Machine Translation Task EMNLP 2022 switch-GLAT: Multilingual Parallel Machine Translation Via Code-Switch Decoder ICLR 2022 Cross-modal Contrastive Learning for Speech Translation NAACL 2022 STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation ACL 2022 Rethinking Document-level Neural Machine Translation ACL 2022 Leveraging Pseudo-labeled Data to Improve Direct Speech-to-Speech Translation INTERSPEECH 2022 Learning When to Translate for Streaming Speech ACL 2022 The Volctrans GLAT System: Non-autoregressive Translation Meets WMT21 EMNLP 2021 Consecutive Decoding for Speech-to-text Translation AAAI 2021 Listen, Understand and Translate: Triple Supervision Decouples End-to-end Speech-to-text Translation AAAI 2021 Finding Sparse Structures for Domain Specific Neural Machine Translation AAAI 2021 Contrastive Learning for Many-to-many Multilingual Neural Machine Translation ACL 2021 Learning Language Specific Sub-network for Multilingual Machine Translation ACL 2021 Glancing Transformer for Non-Autoregressive Neural Machine Translation ACL 2021 NeurST: Neural Speech Translation Toolkit ACL 2021 Pre-training Methods for Neural Machine Translation ACL 2021 Learning Shared Semantic Space for Speech-to-Text Translation ACL 2021 Language Tags Matter for Zero-Shot Neural Machine Translation ACL 2021 The Volctrans Neural Speech Translation System for IWSLT 2021 ACL 2021 Learning Kernel-Smoothed Machine Translation with Retrieved Examples EMNLP 2021 Multilingual Translation via Grafting Pre-trained Language Models EMNLP 2021 Counter-Interference Adapter for Multilingual Machine Translation EMNLP 2021 Secoco: Self-Correcting Encoding for Neural Machine Translation EMNLP 2021 Contrastive Learning for Many-to-many Multilingual Neural Machine Translation IJCNLP 2021 Learning Language Specific Sub-network for Multilingual Machine Translation IJCNLP 2021 Glancing Transformer for Non-Autoregressive Neural Machine Translation IJCNLP 2021 NeurST: Neural Speech Translation Toolkit IJCNLP 2021 Pre-training Methods for Neural Machine Translation IJCNLP 2021 Learning Shared Semantic Space for Speech-to-Text Translation IJCNLP 2021 Language Tags Matter for Zero-Shot Neural Machine Translation IJCNLP 2021 The Volctrans Neural Speech Translation System for IWSLT 2021 IJCNLP 2021 End-to-End Speech Translation via Cross-Modal Progressive Training INTERSPEECH 2021 Generative Imagination Elevates Machine Translation NAACL 2021 Cross-lingual Supervision Improves Unsupervised Neural Machine Translation NAACL 2021 Autocorrect in the Process of Translation — Multi-task Learning Improves Dialogue Machine Translation NAACL 2021 LightSeq: A High Performance Inference Library for Transformers NAACL 2021 Towards Making the Most of BERT in Neural Machine Translation AAAI 2020 Active Sentence Learning by Adversarial Uncertainty Sampling in Discrete Space EMNLP 2020 The Volctrans Machine Translation System for WMT20 EMNLP 2020 Volctrans Parallel Corpus Filtering System for WMT 2020 EMNLP 2020 Xiaomingbot: A Multilingual Robot News Reporter ACL 2020 Pre-training Multilingual Neural Machine Translation by Leveraging Alignment Information EMNLP 2020 Improving Maximum Likelihood Training for Text Generation with Density Ratio Estimation AISTATS 2020 On the Sentence Embeddings from Pre-trained Language Models EMNLP 2020 Towards Linear Time Neural Machine Translation with Capsule Networks EMNLP 2019 Imitation Learning for Non-Autoregressive Neural Machine Translation ACL 2019 Towards Linear Time Neural Machine Translation with Capsule Networks IJCNLP 2019 Neural Machine Translation with Decoding History Enhanced Attention COLING 2018 Tencent Neural Machine Translation Systems for WMT18 EMNLP 2018 Incorporating Word Reordering Knowledge into Attention-based Neural Machine Translation ACL 2017 Deep Neural Machine Translation with Linear Associative Unit ACL 2017 Memory-enhanced Decoder for Neural Machine Translation EMNLP 2016 Encoding Source Language with Convolutional Neural Network for Machine Translation ACL 2015 Syntax-Based Deep Matching of Short Texts IJCAI 2015 genCNN: A Convolutional Architecture for Word Sequence Prediction ACL 2015 Encoding Source Language with Convolutional Neural Network for Machine Translation IJCNLP 2015 genCNN: A Convolutional Architecture for Word Sequence Prediction IJCNLP 2015