Прати
Zhengrui Ma
Zhengrui Ma
Верификована је имејл адреса на ict.ac.cn
Наслов
Навело
Навело
Година
BayLing: Bridging Cross-lingual Alignment and Instruction Following through Interactive Translation for Large Language Models
S Zhang, Q Fang, Z Zhang, Z Ma, Y Zhou, L Huang, M Bu, S Gui, Y Chen, ...
arXiv preprint arXiv:2306.10968, 2023
81*2023
Towards Clustering-friendly Representations: Subspace Clustering via Graph Filtering
Z Ma, Z Kang, G Luo, L Tian, W Chen
ACM Multimedia 2020, 2020
572020
Llama-omni: Seamless speech interaction with large language models
Q Fang, S Guo, Y Zhou, Z Ma, S Zhang, Y Feng
arXiv preprint arXiv:2409.06666, 2024
442024
Smoothed multi-view subspace clustering
P Chen, L Liu, Z Ma, Z Kang
Neural Computing for Advanced Applications: Second International Conference …, 2021
222021
Prediction Difference Regularization against Perturbation for Neural Machine Translation
D Guo, Z Ma, M Zhang, Y Feng
Proceedings of ACL 2022, 2022
152022
Viterbi Decoding of Directed Acyclic Transformer for Non-Autoregressive Machine Translation
C Shao, Z Ma, Y Feng
Findings of EMNLP 2022, 2022
152022
Non-autoregressive Streaming Transformer for Simultaneous Translation
Z Ma, S Zhang, S Guo, C Shao, M Zhang, Y Feng
Proceedings of EMNLP 2023, 2023
132023
StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning
S Zhang, Q Fang, S Guo, Z Ma, M Zhang, Y Feng
Proceedings of ACL 2024, 2024
122024
Non-autoregressive Machine Translation with Probabilistic Context-free Grammar
S Gui, C Shao, Z Ma, X Zhang, Y Chen, Y Feng
NeurIPS 2023, 2023
102023
Agent-SiMT: Agent-assisted Simultaneous Machine Translation with Large Language Models
S Guo, S Zhang, Z Ma, M Zhang, Y Feng
arXiv preprint arXiv:2406.06910, 2024
9*2024
A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Any Translation
Z Ma, Q Fang, S Zhang, S Guo, Y Feng, M Zhang
Proceedings of ACL 2024, 2024
92024
Fuzzy alignments in directed acyclic graph for non-autoregressive machine translation
Z Ma, C Shao, S Gui, M Zhang, Y Feng
ICLR 2023, 2023
92023
Learning Monotonic Attention in Transducer for Streaming Generation
Z Ma, Y Feng, M Zhang
arXiv preprint arXiv:2411.17170, 2024
12024
Can We Achieve High-quality Direct Speech-to-Speech Translation without Parallel Speech Data?
Q Fang, S Zhang, Z Ma, M Zhang, Y Feng
Proceedings of ACL 2024, 2024
12024
CTC-based Non-autoregressive Textless Speech-to-Speech Translation
Q Fang, Z Ma, Y Zhou, M Zhang, Y Feng
Findings of ACL 2024, 2024
12024
Beyond MLE: Convex Learning for Text Generation
C Shao, Z Ma, M Zhang, Y Feng
NeurIPS 2023, 2023
12023
Систем тренутно не може да изврши ову радњу. Пробајте поново касније.
Чланци 1–16