Shoutao Guo, Shaolei Zhang, Qingkai Fang, Zhengrui Ma, Min Zhang, Yang Feng. FastLongSpeech: Enhancing Large Speech-Language Models for Efficient Long-Speech Processing. Thirty-Ninth Conference on Neural Information Processing Systems (NeurIPS 2025). December 2nd to December 7th, San Diego, US.
Zhengrui Ma, Yang Feng, Chenze Shao, Fandong Meng, Jie Zhou, Min Zhang.Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space. Thirty-Ninth Conference on Neural Information Processing Systems (NeurIPS 2025). December 2nd to December 7th, San Diego, US.
Kangyu Qiao, Shaolei Zhang, Yang Feng. IG-Pruning: Input-Guided Block Pruning for Large Language Models. The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025) November 4th to November 9th, 2025, Suzhou, China.
Mengyu Bu, Shaolei Zhang, Zhongjun He, Hua Wu, Yang Feng. AlignX: Advancing Multilingual Large Language Models with Multilingual Representation Alignment. The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025), November 4th to November 9th, 2025, Suzhou, China.
Andong Chen, Kehai Chen, Yang Xiang, Xuefeng Bai, Muyun Yang, Yang Feng, Tiejun Zhao, Min Zhang. LLM-based Translation Inference with Iterative Bilingual Understanding. The 63rd Annual Meeting of the Association for Computational Linguistics (Findings of ACL 2025), July 27–August 1st, 2025, Vienna, Austria, pdf
Zhuocheng Zhang, Yang Feng, Min Zhang. FlexRAG: A Flexible and Comprehensive Framework for Retrieval-Augmented Generation. The 63rd Annual Meeting of the Association for Computational Linguistics (System Demonstration of ACL 2025), July 27–August 1st, 2025, Vienna, Austria, pdf
Qingkai Fang, Yan Zhou, Shoutao Guo, Shaolei Zhang, Yang Feng. LLaMA-Omni 2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis. The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), July 27–August 1st, 2025, Vienna, Austria, pdf
Zhengrui Ma, Yang Feng, Min Zhang. Overcoming Non-monotonicity in Transducer-based Streaming Generation. The Forty-Second International Conference on Machine Learning（ICML 2025) , July 13th-July 19th, 2025, Vancouver, BC, Canada, pdf
Shoutao Guo, Shaolei Zhang, Zhengrui Ma, Min Zhang, Yang Feng. Agent-SiMT: Agent-assisted Simultaneous Translation with Large Language Models. IEEE Transactions on Audio, Speech and Language Processing (TASLP), 1-10, pdf
Shaolei Zhang, Shoutao Guo, Qingkai Fang, Yan Zhou, Yang Feng. Stream-Omni: Simultaneous Multimodal Interactions with Large Language-Vision-Speech Model. arXiv, Jun 16, 2025, pdf
Zhengrui Ma, Yang Feng, Chenze Shao, Fandong Meng, Jie Zhou, Min Zhang. Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space. arXiv, May 19, 2025, pdf
Langlin Huang, Mengyu Bu, Yang Feng. MoCE:Adaptive Mixture of Contextualization Experts for Byte-based Neural Machine Translation. 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics. (NAACL 2025), April 29–May 4, 2025，1011–1028, Albuquerque, New Mexico, pdf
Qingkai Fang, Shoutao Guo, Yan Zhou, Zhengrui Ma, Shaolei Zhang, Yang Feng. LLaMA-Omni: Seamless Speech Interaction with Large Language Models. The 13th International Conference on Learning Representations (ICLR 2025), April 24-28, 2025, Singapore, pdf
Shaolei Zhang, Qingkai Fang, Zhe Yang, Yang Feng. LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token. The 13th International Conference on Learning Representations (ICLR 2025), April 24-28, 2025, Singapore, pdf