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}
}

@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}
}

@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}
}

@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}
}

@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{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}
}

@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}
}