@inproceedings{xu-etal-2025-enabling,
    title = "Enabling Real-Time Conversations with Minimal Training Costs",
    author = "Xu, Wang  and
      Wang, Haoyu  and
      Wang, Shuo  and
      Zhao, Weilin  and
      Han, Xu  and
      Yan, Yukun  and
      Zhao, Haiyan  and
      Zhang, Yudi  and
      Tao, Zhe  and
      Liu, Zhiyuan  and
      Che, Wanxiang",
    editor = "Sun, Maosong  and
      Duan, Peiyong  and
      Liu, Zhiyuan  and
      Xu, Ruifeng  and
      Sun, Weiwei",
    booktitle = "Proceedings of the 24th {C}hina National Conference on Computational Linguistics ({CCL} 2025)",
    month = aug,
    year = "2025",
    address = "Jinan, China",
    publisher = "Chinese Information Processing Society of China",
    url = "https://preview.aclanthology.org/ingest-ccl/2025.ccl-1.85/",
    pages = "1136--1147",
    abstract = "``Large language models (LLMs) have demonstrated the ability to improve human efficiency through conversational interactions. Conventional LLM-powered dialogue systems, operating ona turn-based paradigm, preclude real-time interaction during response generation. To address this limitation, researchers have proposed duplex models. These models can dynamically adapt to user input, facilitating real-time interactive feedback. However, these methods typically require substantial computational resources to acquire the duplex capability. To reduce overhead, this paper presents a new duplex decoding approach that enhances LLMs with duplex ability, requiring minimal additional training. Specifically, our method employs parallel decoding of input and responses in conversations, effectively implementing a channel-division-multiplexing decoding strategy. Experimental results indicate that our proposed method significantly enhances the naturalness and human-likeness of user-AI interactions with minimal training costs.''"
}