Tsinghua - Jin Xu
I am currently leading the audio group at Alibaba Qwen Group, responsible for research on large-scale speech synthesis, general audio synthesis, general speech understanding, and chat models centered on audio. Prior to this, I was a Ph.D. student of Institute for Interdisciplinary Information Sciences (IIIS) at Tsinghua University (Beijing), researching large model automatic architecture search, low-resource speech synthesis and recognition, repetition problems in autoregressive language models, and applications of graph models. My doctoral advisor was Associate Professor Prof. Jian Li. I got BSc degree from Beijing of Posts and Telecommunication University in 2018. During my undergraduate, I ranked first (1/565) and obtained the Special Scholarship (1/1600). Currently, I have published dozens of papers at top international AI conferences such as ICLR, ICML, NeurIPS, and KDD.
News: We are looking for interns or FTEs working for speech synthesis and audio chat models. Please send the email to jxu3425 dot gmail dot com
Internship
- 2019.09 - 2020.10 Microsoft Research Asia. Full-time Research Intern
Supervisor: Xu Tan, Tao Qin - 2018.07 - 2019.02 Business Intelligence Lab, Baidu. Full-time Research Intern
Supervisor: Jingbo Zhou, Hui Xiong
Award
- 2020 Rank 1st - KDDCUP AutoGraph Competition
- 2015 First Prize - Mathematical Contest in Modeling
- 2015 First Prize - University Students Physics Competition in Parts of the Country
Publications & Preprints
2024
Qwen2-Audio Technical Report Arxiv Preprint Yunfei Chu*, Jin Xu*, Qian Yang*, Haojie Wei, Xipin Wei, Zhifang Guo, Yichong Leng, Yuanjun Lv, Jinzheng He, Junyang Lin, Chang Zhou, Jingren Zhou [PDF] |
Qwen2 Technical Report Arxiv Preprint An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, Guanting Dong, Haoran Wei, Huan Lin, Jialong Tang, Jialin Wang, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Ma, Jin Xu, Jingren Zhou, Jinze Bai, Jinzheng He, Junyang Lin, Kai Dang, Keming Lu, Keqin Chen, Kexin Yang, Mei Li, Mingfeng Xue, Na Ni, Pei Zhang, Peng Wang, Ru Peng, Rui Men, Ruize Gao, Runji Lin, Shijie Wang, Shuai Bai, Sinan Tan, Tianhang Zhu, Tianhao Li, Tianyu Liu, Wenbin Ge, Xiaodong Deng, Xiaohuan Zhou, Xingzhang Ren, Xinyu Zhang, Xipin Wei, Xuancheng Ren, Yang Fan, Yang Yao, Yichang Zhang, Yu Wan, Yunfei Chu, Yuqiong Liu, Zeyu Cui, Zhenru Zhang, Zhihao Fan [PDF] |
AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension ACL 2024 Qian Yang*, Jin Xu*, Wenrui Liu, Yunfei Chu, Ziyue Jiang, Xiaohuan Zhou, Yichong Leng, Yuanjun Lv, Zhou Zhao, Chang Zhou, Jingren Zhou [PDF] |
Understanding In-Context Learning from Repetitions ICLR Jianhao Yan, Jin Xu, Chiyu Song, Chenming Wu, Yafu Li, Yue Zhang [PDF] |
2023
Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models Arxiv Preprint Yunfei Chu*, Jin Xu*, Xiaohuan Zhou*, Qian Yang, Shiliang Zhang, Zhijie Yan, Chang Zhou, Jingren Zhou [PDF] |
Qwen technical report Arxiv Preprint Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, Binyuan Hui, Luo Ji, Mei Li, Junyang Lin, Runji Lin, Dayiheng Liu, Gao Liu, Chengqiang Lu, Keming Lu, Jianxin Ma, Rui Men, Xingzhang Ren, Xuancheng Ren, Chuanqi Tan, Sinan Tan, Jianhong Tu, Peng Wang, Shijie Wang, Wei Wang, Shengguang Wu, Benfeng Xu, Jin Xu, An Yang, Hao Yang, Jian Yang, Shusheng Yang, Yang Yao, Bowen Yu, Hongyi Yuan, Zheng Yuan, Jianwei Zhang, Xingxuan Zhang, Yichang Zhang, Zhenru Zhang, Chang Zhou, Jingren Zhou, Xiaohuan Zhou, Tianhang Zhu [PDF] |
LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT Arxiv Preprint Qian Chen, Yunfei Chu, Zhifu Gao, Zerui Li, Kai Hu, Xiaohuan Zhou, Jin Xu, Ziyang Ma, Wen Wang, Siqi Zheng, Chang Zhou, Zhijie Yan, Shiliang Zhang [PDF] |
DC-MBR: Distributional Cooling for Minimum Bayesian Risk Decoding COLING Jianhao Yan, Jin Xu, Fandong Meng, Jie Zhou, Yue Zhang [PDF] |
Effective Graph Learning with Adaptive Knowledge Exchange CIKM Liang Zeng*, Jin Xu*, Zijun Yao, Yanqiao Zhu, Jian Li [PDF] |
2022
Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation NeurlPS 2022 Jin Xu, Xiaojiang Liu, Jianhao Yan, Deng Cai, Huayang Li, Jian Li [PDF] |
Analyzing and Mitigating Interference in Neural Architecture Search ICML, Spotlight Jin Xu, Xu Tan, Kaitao Song, Renqian Luo, Yichong Leng, Tao Qin, Tie-Yan Liu, Jian Li [PDF] |
AutoHEnsGNN: Winning Solution to AutoGraph Challenge for KDD Cup 2020 ICDE Jin Xu*, Mingjian Chen*, Jianqiang Huang, Xingyuan Tang, Ke Hu, Jian Li, Jia Cheng, Jun Lei [PDF] |
2021
NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search KDD Jin Xu, Xu Tan, Renqian Luo, Kaitao Song, Jian Li, Tao Qin, Tie-Yan Liu [PDF] |
FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition EMNLP Findings Yichong Leng, Xu Tan, Rui Wang, Linchen Zhu, Jin Xu, Wenjie Liu, Linquan Liu, Xiang-Yang Li, Tao Qin, Edward Lin, Tie-Yan Liu [PDF] |
FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition NeurIPS Yichong Leng, Xu Tan, Linchen Zhu, Jin Xu, Renqian Luo, Linquan Liu, Tao Qin, Xiang-Yang Li, Ed Lin, Tie-Yan Liu [PDF] |
Speech-T: Transducer for Text to Speech and Beyond NeurIPS Jiawei Chen, Xu Tan, Yichong Leng, Jin Xu, Guihua Wen, Tao Qin, Tie-Yan Liu [PDF] |
MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognition ICASSP Linghui Meng, Jin Xu, Xu Tan, Jindong Wang, Tao Qin, Bo Xu [PDF] |
2020
LRSpeech: Extremely low-resource speech synthesis and recognition KDD Jin Xu, Xu Tan, Yi Ren, Tao Qin, Jian Li, Sheng Zhao, Tie-Yan Liu [PDF] |
An Adaptive Master-Slave Regularized Model for Unexpected Revenue Prediction Enhanced with Alternative Data ICDE, Oral Jin Xu, Jingbo Zhou, Yongpo Jia, Jian Li, Xiong Hui [PDF] |
Multispeech: Multi-speaker text to speech with transformer InterSpeech Mingjian Chen, Xu Tan, Yi Ren, Jin Xu, Hao Sun, Sheng Zhao, Tao Qin, Tie-Yan Liu [PDF] |
2019
A collaborative learning framework to tag refinement for points of interest KDD Jingbo Zhou, Shan Gou, Renjun Hu, Dongxiang Zhang, Jin Xu, Airong Jiang, Ying Li, Hui Xiong [PDF] |