Xuanjun Chen (陳炫均)

@misc{chen2026llmagents,
    title={Can LLM Agents Automate Reinforcement Learning for Text-to-Speech?},
    author={Xuanjun Chen and Zixiong Su and Hao Shi and Chang Zeng and Kai Li and Jyh-Shing Roger Jang and Hung-yi Lee},
    year={2026},
    month={October},
    eprint={2610.04488},
    archivePrefix={arXiv},
    note={Technical Report}
}

@misc{chen2026metabench,
    title={MetaBench-Harness: Unlocking End-to-End Optimization of Benchmark Harnesses},
    author={Xuanjun Chen and Hua-Hsuan Chen and Wei-Chung Lu and Yinghao Ma and Jyh-Shing Roger Jang and Hung-yi Lee},
    year={2026},
    month={September},
    eprint={2609.33411},
    archivePrefix={arXiv}
}

@misc{wu2024towards,
    title={Towards audio language modeling - an overview},
    author={Haibin Wu and Xuanjun Chen and Yi-Cheng Lin and Kai-wei Chang and Ho-Lam Chung and Alexander Liu and Hung-yi Lee},
    year={2024},
    eprint={2402.13236},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

@article{cyli2026codarag,
    title={CodaRAG: Connecting the Dots with Associativity Inspired by Complementary Learning},
    author={Cheng-Yen Li and Xuanjun Chen and Claire Lin and Wei-Yu Chen and Wenhua Nie and Hung-yi Lee and Jyh-Shing Roger Jang},
    journal={ACM Transactions on Intelligent Systems and Technology},
    year={2026}
}

@ARTICLE{chen2026codecfake,
author={Chen, Xuanjun and Du, Jiawei and Wu, Haibin and Zhang, Lin and Lin, I-Ming and Chiu, I-Hsiang and Ren, Wenze and Tseng, Yuan and Tsao, Yu and Jang, Jyh-Shing Roger and Lee, Hung-yi},
journal={IEEE Transactions on Audio, Speech and Language Processing},
title={CodecFake+: Codec-Based Resynthesized Data as a Proxy for Detecting CodecFake Speech},
year={2026},
volume={34},
pages={2929--2944},
doi={10.1109/TASLPRO.2026.3692291}
}

@ARTICLE{lu2026desta25,
author={Lu, Ke-Han and Chen, Zhehuai and Fu, Szu-Wei and Yang, Chao-Han Huck and Huang, Sung-Feng and Yang, Chih-Kai and Yu, Chee-En and Chen, Chun-Wei and Chen, Wei-Chih and Huang, Chien-yu and Lin, Yi-Cheng and Lin, Yu-Xiang and Fu, Chi-An and Kuan, Chun-Yi and Ren, Wenze and Chen, Xuanjun and Huang, Wei-Ping and Hu, En-Pei and Lin, Tzu-Quan and Wu, Yuan-Kuei and Huang, Kuan-Po and Huang, Hsiao-Ying and Chou, Huang-Cheng and Chang, Kai-Wei and Chiang, Cheng-Han and Ginsburg, Boris and Wang, Yu-Chiang Frank and Lee, Hung-yi},
journal={IEEE Transactions on Audio, Speech and Language Processing},
title={DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model With Self-Generated Cross-Modal Alignment},
year={2026},
volume={34},
pages={2062--2076},
doi={10.1109/TASLPRO.2026.3675792}
}

@inproceedings{chou2026efficient,
    title={Only Ask What You Don't Know: Grounded Delta Planning for Efficient Multi-step RAG},
    author={Wei-Chieh Chou and Xuanjun Chen and Jian-Ren Lin and Claire Lin and Hung-yi Lee and Jyh-Shing Roger Jang},
    booktitle={Third Conference on Language Modeling (COLM)},
    year={2026}
}

@inproceedings{huang2025dynamic,
    title={Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the <br> Capabilities of Spoken Language Models with 180 Tasks},
    author={Chien-yu Huang and Wei-Chih Chen and Shu-wen Yang and Andy T. Liu and Chen-An Li and Yu-Xiang Lin and Wei-Cheng Tseng and Anuj Diwan and Yi-Jen Shih and Jiatong Shi and William Chen and Chih-Kai Yang and Wenze Ren and Xuanjun Chen and Chi-Yuan Hsiao and Puyuan Peng and Shih-Heng Wang and Chun-Yi Kuan and Ke-Han Lu and Kai-Wei Chang and Fabian Ritter-Gutierrez and Kuan-Po Huang and Siddhant Arora and You-Kuan Lin and Ming To Chuang and Eunjung Yeo and Kalvin Chang and Chung-Ming Chien and Kwanghee Choi and Jun-You Wang and Cheng-Hsiu Hsieh and Yi-Cheng Lin and Chee-En Yu and I-Hsiang Chiu and Heitor R. Guimarães and Jionghao Han and Tzu-Quan Lin and Tzu-Yuan Lin and Homu Chang and Ting-Wu Chang and Chun Wei Chen and Shou-Jen Chen and Yu-Hua Chen and Hsi-Chun Cheng and Kunal Dhawan and Jia-Lin Fang and Shi-Xin Fang and Kuan-Yu Fang Chiang and Chi An Fu and Hsien-Fu Hsiao and Ching Yu Hsu and Shao-Syuan Huang and Lee Chen Wei and Hsi-Che Lin and Hsuan-Hao Lin and Hsuan-Ting Lin and Jian-Ren Lin and Ting-Chun Liu and Li-Chun Lu and Tsung-Min Pai and Ankita Pasad and Shih-Yun Shan Kuan and Suwon Shon and Yuxun Tang and Yun-Shao Tsai and Jui-Chiang Wei and Tzu-Chieh Wei and Chengxi Wu and Dien-Ruei Wu and Chao-Han Huck Yang and Chieh-Chi Yang and Jia Qi Yip and Shao-Xiang Yuan and Vahid Noroozi and Zhehuai Chen and Haibin Wu and Karen Livescu and David Harwath and Shinji Watanabe and Hung-yi Lee},
    booktitle={International Conference on Learning Representations},
    year={2025},
    url={https://openreview.net/forum?id=s7lzZpAW7T}
}

@inproceedings{wu-etal-2024-codec,
    title = "Codec-{SUPERB}: An In-Depth Analysis of Sound Codec Models",
    author = "Wu, Haibin  and Chung, Ho-Lam  and Lin, Yi-Cheng  and Wu, Yuan-Kuei  and Chen, Xuanjun  and Pai, Yu-Chi  and Wang, Hsiu-Hsuan  and Chang, Kai-Wei  and Liu, Alexander  and Lee, Hung-yi",
    editor = "Ku, Lun-Wei  and Martins, Andre  and Srikumar, Vivek",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
    year = "2024",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.findings-acl.616/",
    doi = "10.18653/v1/2024.findings-acl.616",
    pages = "10330--10348",
}

@article{chen2026joint,
  title={Joint Fullband-Subband Modeling for High-Resolution SingFake Detection},
  author={Chen, Xuanjun and Hu, Chia-Yu and Huang, Sung-Feng and Wu, Haibin and Lee, Hung-yi and Jang, Jyh-Shing Roger},
  journal={arXiv preprint arXiv:2604.04841},
  year={2026}
}

@misc{chen2025how,
    title={How Does Instrumental Music Help SingFake Detection?},
    author={Xuanjun Chen and Chia-Yu Hu and I-Ming Lin and Yi-Cheng Lin and I-Hsiang Chiu and You Zhang and Sung-Feng Huang and Yi-Hsuan Yang and Haibin Wu and Hung-yi Lee and Jyh-Shing Roger Jang},
    year={2025},
    eprint={2509.14675},
    archivePrefix={arXiv},
    primaryClass={cs.SD}
}

@inproceedings{chen2025towards,
    title={Towards Generalized Source Tracing for Codec-Based Deepfake Speech},
    author={Xuanjun Chen and I-Ming Lin and Lin Zhang and Haibin Wu and Hung-yi Lee and Jyh-Shing Roger Jang},
    booktitle={2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)},
    year={2025}
}

@inproceedings{chen2025codecbased,
    title={Codec-Based Deepfake Source Tracing via Neural Audio Codec Taxonomy},
    author={Xuanjun Chen and I-Ming Lin and Lin Zhang and Jiawei Du and Haibin Wu and Hung-yi Lee and Jyh-Shing Roger Jang},
    booktitle={Interspeech 2025},
    year={2025},
    url={https://www.isca-archive.org/interspeech_2025/chen25j_interspeech.pdf}
}

@inproceedings{chen2024singing,
    title={Singing Voice Graph Modeling for SingFake Detection},
    author={Xuanjun Chen and Haibin Wu and Jyh-Shing Roger Jang and Hung-yi Lee},
    booktitle={Interspeech 2024},
    year={2024},
    url={https://www.isca-archive.org/interspeech_2024/chen24o_interspeech.pdf}
}