Zhaopeng Tu Principal Researcher Tencent AI Lab tuzhaopeng@gmail.com

Bio

Zhaopeng Tu is a principal researcher at Tencent AI Lab, whose research focuses on deep learning for natural language processing (NLP). He is currently working on neural machine translation (NMT) and large language modeling (LLM). He has published over 100 papers in leading NLP/AI journals and conferences such as ICML, ACL, EMNLP, ICLR, and TACL. He served as Associate Editor of NeuroComputing, Area Chair or Senior PC Member of ACL, EMNLP, NAACL, AAAI, and IJCAI.

News

• 2024-10: Our paper titled "GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generation" was nominated for the Best Paper Award at ACM MM 2024.
• 2024-10: 1 paper was accepted to Transactions of ACL, and 1 paper was accepted to IEEE/ACM Transactions on Audio, Speech, and Language Processing.
• 2024-09: 1 paper was accepted to EMNLP2024, and 3 papers (including 2 D&B Papers) were accepted to NeurIPS2024.
• 2024-07: 1 paper was accepted to ACM-MM2024, and 2 papers were accepted to ECAI2024.
• 2024-05: 1 paper was accepted to ICML2024, and 6 papers were accepted to ACL2024.
• 2024-01: 2 papers were accepted to ICLR2024.
• 2023-10: 3 papers were accepted to EMNLP2023.
• 2023-05: 2 papers were accepted to ACL2023.
• 2022-11: Our paper titled "Adapters for Enhanced Modeling of Multilingual Knowledge and Text" was selected as the Best Paper Award at MRL Workshop in EMNLP2022.
• 2022-10: 3 papers were accepted to EMNLP2022.
• 2022-02: 3 papers were accepted to ACL2022.

Selected Publications

Large Language Models

• Wenxiang Jiao, Wenxuan Wang, Jen-tse Huang, Xing Wang, and Zhaopeng Tu. Is ChatGPT A Good Translator? Yes With GPT-4 As The Engine. Preprint.
• Zhanyu Wang, Longyue Wang, Zhen Zhao, Minghao Wu, Chenyang Lyu, Huayang Li, Deng Cai, Luping Zhou, Shuming Shi, and Zhaopeng Tu. GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generation. ACM MM 2024. [Best Paper Normination]
• Tian Liang, Zhiwei He, Wenxiang Jiao, Xing Wang, Yan Wang, Rui Wang, Yujiu Yang, Shuming Shi, and Zhaopeng Tu. Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate. EMNLP 2024.
• Cunxiao Du, Jing Jiang, Xu Yuanchen, Jiawei Wu, Sicheng Yu, Yongqi Li, Shenggui Li, Kai Xu, Liqiang Nie, Zhaopeng Tu*, and Yang You. GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decoding. ICML 2024.
• Jen-tse Huang, Man Ho LAM, Eric John Li, Shujie Ren, Wenxuan Wang, Wenxiang Jiao, Zhaopeng Tu, and Michael Lyu. Apathetic or Empathetic? Evaluating LLMs' Emotional Alignments with Humans. NeurIPS 2024.
• Wenxuan Wang, Wenxiang Jiao, Jingyuan Huang, Ruyi Dai, Jen-tse Huang, Zhaopeng Tu*, and Michael R Lyu. Not All Countries Celebrate Thanksgiving: On the Cultural Dominance in Large Language Models. ACL 2024.
• Zhiwei He, Binglin Zhou, Hongkun Hao, Aiwei Liu, Xing Wang, Zhaopeng Tu, Zhuosheng Zhang, and Rui Wang. On the Cross-lingual Consistency of Text Watermark for Large Language Models. ACL 2024.
• Wenxuan Wang, Zhaopeng Tu, Chang Chen, Youliang Yuan, Jen-tse Huang, Wenxiang Jiao, and Michael R Lyu. All Languages Matter: On the Multilingual Safety of Large Language Models. ACL 2024 (Findings).
• Zefeng Du, Wenxiang Jiao, Longyue Wang, Chenyang Lyu, Jianhui Pang, Leyang Cui, Kaiqiang Song, Derek F. Wong, Shuming Shi, and Zhaopeng Tu. Benchmarking and Improving Long-Text Translation with Large Language Models. ACL 2024 (Findings).
• Jen-tse Huang, Wenxuan Wang, Eric John Li, Man Ho LAM, Shujie Ren, Youliang Yuan, Wenxiang Jiao, Zhaopeng Tu, and Michael Lyu. On the Humanity of Conversational AI: Evaluating the Psychological Portrayal of LLMs. ICLR 2024 (Oral, 1.2%).
• Youliang Yuan, Wenxiang Jiao, Wenxuan Wang, Jen-tse Huang, Pinjia He, Shuming Shi, and Zhaopeng Tu. GPT-4 is too Smart to be Safe: Stealthy Chat with LLMs via Cipher. ICLR 2024.
• Zhiwei He, Tian Liang, Wenxiang Jiao, Zhuosheng Zhang, Yujiu Yang, Rui Wang, Zhaopeng Tu*, Shuming Shi, and Xing Wang. Exploring Human-Like Translation Strategy with Large Language Models. TACL 2024.
• Zhiwei He, Xing Wang, Wenxiang Jiao, Zhuosheng Zhang, Rui Wang, Shuming Shi, and Zhaopeng Tu. Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model. NAACL 2024.
• Longyue Wang, Chenyang Lyu, Tianbo Ji, Zhirui Zhang, Dian Yu, Shuming Shi, and Zhaopeng Tu. Document-Level Machine Translation with Large Language Models. EMNLP 2023.
• Wenxiang Jiao, Jen-tse Huang, Wenxuan Wang, Xing Wang, Shuming Shi, and Zhaopeng Tu. ParroT: Translating During Chat Using Large Language Models. EMNLP 2023 (Findings).

Autoregreesive NMT

• Zhaopeng Tu, Zhengdong Lu, Yang Liu, Xiaohua Liu, and Hang Li. Modeling Coverage for Neural Machine Translation. ACL 2016. [code]
• Zhaopeng Tu, Yang Liu, Zhengdong Lu, Xiaohua Liu, and Hang Li. Context Gates for Neural Machine Translation. TACL 2017. [code]
• Zhaopeng Tu, Yang Liu, Lifeng Shang, Xiaohua Liu, and Hang Li. Neural Machine Translation with Reconstruction. AAAI 2017. [code]
• Longyue Wang, Zhaopeng Tu*, Andy Way, and Qun Liu. Exploiting Cross-Sentence Context for Neural Machine Translation. EMNLP 2017 (Short).
• Zhaopeng Tu, Yang Liu, Shuming Shi, and Tong Zhang. Learning to Remember Translation History with a Continuous Cache. TACL 2018.

Non-Autoregreesive NMT

• Cunxiao Du, Zhaopeng Tu*, and Jing Jiang. Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation. ICML 2021 (Oral, 3%).
• Cunxiao Du, Zhaopeng Tu*, Longyue Wang, and Jing Jiang. ngram-OAXE: Phrase-Based Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation. COLING 2022.
• Liang Ding, Longyue Wang, Xuebo Liu, Derek F. Wong, Dacheng Tao, and Zhaopeng Tu. Understanding and Improving Lexical Choice in Non-Autoregressive Translation. ICLR 2021.
• Liang Ding, Longyue Wang, Xuebo Liu, Derek F. Wong, Dacheng Tao, and Zhaopeng Tu. Rejuvenating Low-Frequency Words: Making the Most of Parallel Data in Non-Autoregressive Translation. ACL 2021.
• Liang Ding, Longyue Wang, Shuming Shi, Dacheng Tao, and Zhaopeng Tu. Redistributing Low-Frequency Words: Making the Most of Monolingual Data in Non-Autoregressive Translation. ACL 2022.