Xuanjun Chen (陳炫均)

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

@misc{chen2026lalm,
    title={What Does LALM Post-training Learn? Rethinking Audio Understanding and Reasoning Capabilities},
    author={Chen, Hua-Hsuan and Chen, Xuanjun and Lu, Wei-Chung and Yang, Chih-Kai and Lin, Yu-Xiang and Huang, Sung-Feng and Wu, Haibin and Lee, Hung-yi},
    year={2026},
    eprint={2610.19476},
    archivePrefix={arXiv},
    primaryClass={cs.SD}
}

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

@article{lu2026desta25,
    title={DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model With Self-Generated Cross-Modal Alignment},
    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},
    volume={34},
    pages={2062--2076},
    year={2026},
    doi={10.1109/TASLPRO.2026.3675792}
}

@inproceedings{huang2025dynamic,
    title={Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks},
    author={Huang, Chien-yu and Chen, Wei-Chih and Yang, Shu-wen and Liu, Andy T. and Li, Chen-An and Lin, Yu-Xiang and Tseng, Wei-Cheng and Diwan, Anuj and Shih, Yi-Jen and Shi, Jiatong and Chen, William and Yang, Chih-Kai and Ren, Wenze and Chen, Xuanjun and Hsiao, Chi-Yuan and Peng, Puyuan and Wang, Shih-Heng and Kuan, Chun-Yi and Lu, Ke-Han and Chang, Kai-Wei and Ritter-Gutierrez, Fabian and Huang, Kuan-Po and Arora, Siddhant and Lin, You-Kuan and Chuang, Ming To and Yeo, Eunjung and Chang, Kalvin and Chien, Chung-Ming and Choi, Kwanghee and Wang, Jun-You and Hsieh, Cheng-Hsiu and Lin, Yi-Cheng and Yu, Chee-En and Chiu, I-Hsiang and Guimarães, Heitor R. and Han, Jionghao and Lin, Tzu-Quan and Lin, Tzu-Yuan and Chang, Homu and Chang, Ting-Wu and Chen, Chun Wei and Chen, Shou-Jen and Chen, Yu-Hua and Cheng, Hsi-Chun and Dhawan, Kunal and Fang, Jia-Lin and Fang, Shi-Xin and Chiang, Kuan-Yu Fang and Fu, Chi An and Hsiao, Hsien-Fu and Hsu, Ching Yu and Huang, Shao-Syuan and Wei, Lee Chen and Lin, Hsi-Che and Lin, Hsuan-Hao and Lin, Hsuan-Ting and Lin, Jian-Ren and Liu, Ting-Chun and Lu, Li-Chun and Pai, Tsung-Min and Pasad, Ankita and Kuan, Shih-Yun Shan and Shon, Suwon and Tang, Yuxun and Tsai, Yun-Shao and Wei, Jui-Chiang and Wei, Tzu-Chieh and Wu, Chengxi and Wu, Dien-Ruei and Yang, Chao-Han Huck and Yang, Chieh-Chi and Yip, Jia Qi and Yuan, Shao-Xiang and Noroozi, Vahid and Chen, Zhehuai and Wu, Haibin and Livescu, Karen and Harwath, David and Watanabe, Shinji and Lee, Hung-yi},
    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},
    booktitle={Findings of the Association for Computational Linguistics: ACL 2024},
    pages={10330--10348},
    year={2024},
    doi={10.18653/v1/2024.findings-acl.616},
    url={https://aclanthology.org/2024.findings-acl.616/}
}

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

@article{cyli2026codarag,
    title={CodaRAG: Connecting the Dots with Associativity Inspired by Complementary Learning},
    author={Li, Cheng-Yen and Chen, Xuanjun and Lin, Claire and Chen, Wei-Yu and Nie, Wenhua and Lee, Hung-yi and Jang, Jyh-Shing Roger},
    journal={ACM Transactions on Intelligent Systems and Technology},
    year={2026},
    doi={10.1145/3859251}
}

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

@article{chen2026codecfake,
    title={CodecFake+: Codec-Based Resynthesized Data as a Proxy for Detecting CodecFake Speech},
    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},
    volume={34},
    pages={2929--2944},
    year={2026},
    doi={10.1109/TASLPRO.2026.3692291}
}

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

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