Elamur Research⌕
☰
home / papers / 2026 / DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding

DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding

Paper · 2026 · Jiaming Zhou, Xuxin Cheng, Shiwan Zhao et al.

Summary

Large audio language models are mostly autoregressive. They need a lot of data and compute to scale, and their token-by-token decoding slows inference. The earlier DIFFA work showed that a diffusion LLM backbone can help audio understanding, but only at a small, proof-of-concept scale. DIFFA-2 develops this into a practical system.

  • Architecture: a frozen Whisper-Large-V3 encoder feeds two adapters. A semantic adapter handles content aligned with text, and a Q-former acoustic adapter captures prosody, emotion, environmental sound and music. Both feed a dLLM backbone built on the LLaDA framework.
  • Training: a four-stage curriculum on fully open-source data. It covers ASR-based semantic alignment, joint semantic–acoustic alignment, LoRA fine-tuning of the backbone, and preference optimization with VRPO.
  • Inference: factor-based parallel decoding speeds up generation.

On MMSU, MMAU and MMAR, DIFFA-2 consistently beats DIFFA and is competitive with strong autoregressive models, while training only a small fraction of its parameters. This suggests diffusion backbones are a realistic, data-efficient option for general audio understanding.

Key points

  • Data budget: about 11,000 hours of ASR data (LibriSpeech, GigaSpeech) plus 3,767 hours of SFT data, roughly 14.8k hours in total. Only around 1.1% of parameters (99M) are trainable.
  • Adapters: the semantic adapter reduces the frame rate from 50 Hz to 12.5 Hz. The acoustic adapter is a two-layer Q-former with 64 learnable queries.
  • Preference data: an LLM generated plausible "rejected" answers containing subtle audio errors, such as the wrong speaker gender or sound event. These pairs were used for VRPO.
  • Ablation against an AR baseline: under identical data and curriculum, DIFFA-2 outperforms LLaMA-Audio (LLaMA 3.1 backbone) on MMAU and MMSU. The AR model keeps a slight edge in ASR word error rate. Parallel decoding pushes DIFFA-2's real-time factor below the AR baseline's.
  • Limitations: performance on VoiceBench (spoken dialogue) is only mid-range. The model does not generate speech or support streaming. It is not faster than AR audio models in every setting.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🏢MeituanBeijing · China26 works · 3,953 citations🎓Nankai UniversityTianjin · China36 works · 762 citations

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 worksSignal Processing · 493 works

🧭 Topics 2Research subjects and languages the work is about.Language models & pretraining · 3,894 worksSpeech & spoken language · 519 works

Cite

Cite as Jiaming Zhou, Xuxin Cheng, Shiwan Zhao, Yuhang Jia, Cao Liu, Ke Zeng, Xunliang Cai and Yong Qin. 2026. DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.235

@inproceedings{zhou2026diffa,
  title = {{DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding}},
  author = {Jiaming Zhou, Xuxin Cheng, Shiwan Zhao, Yuhang Jia, Cao Liu, Ke Zeng, Xunliang Cai and Yong Qin},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.235},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.235}
}

References

75 references, 38 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Adaeze Adigwe, Noé Tits, Kevin El Haddad, Sarah Ostadabbas, and Thierry Dutoit. 2018. The emotional voices database: Towards controlling the emotion dimension in voice generation systems. arXiv preprint arXiv:1806.09514. — [arXiv:1806.09514](https://arxiv.org/abs/1806.09514) find
  2. Andrea Agostinelli, Timo I Denk, Zalán Borsos, Jesse Engel, Mauro Verzetti, Antoine Caillon, Qingqing Huang, Aren Jansen, Adam Roberts, Marco Tagliasacchi, and 1 others. 2023. Musiclm: Generating music from text. arXiv preprint arXiv:2301.11325. — [arXiv:2301.11325](https://arxiv.org/abs/2301.11325) find
  3. Afroz Ahamad, Ankit Anand, and Pranesh Bhargava. 2020. Accentdb: A database of non-native english accents to assist neural speech recognition. In Proceedings of The 12th Language Resources and Evaluation Conference, pages 5353–5360. European Language Resources Association.
  4. Jacob Austin, DanielD. Johnson, Jonathan Ho, Daniel Tarlow, and Riannevanden Berg. 2021. Structured denoising diffusion models in discrete state-spaces. arXiv: Learning,arXiv: Learning.
  5. Jonathan Berant, Andrew Chou, Roy Frostig, and Percy Liang. 2013. Semantic parsing on freebase from question-answer pairs. In Proceedings of the 2013 conference on empirical methods in natural language processing, pages 1533–1544.
  6. Carlos Busso, Murtaza Bulut, Chi-Chun Lee, Abe Kazemzadeh, Emily Mower, Samuel Kim, Jeannette N. Chang, Sungbok Lee, and Shrikanth S. Narayanan. 2008. Iemocap: Interactive emotional dyadic motion capture database. Language Resources and Evaluation, 42(4):335–359. find
  7. Guoguo Chen, Shuzhou Chai, Guanbo Wang, Jiayu Du, Wei-Qiang Zhang, Chao Weng, Dan Su, Daniel Povey, Jan Trmal, Junbo Zhang, and 1 others. 2021. Gigaspeech: An evolving, multi-domain asr corpus with 10,000 hours of transcribed audio. arXiv preprint arXiv:2106.06909. find
  8. Wenxi Chen, Ziyang Ma, Ruiqi Yan, Yuzhe Liang, and et al. 2024a. Slam-omni: Timbre-controllable voice interaction system with single-stage training. arXiv preprint arXiv:2412.15649. find
  9. Yiming Chen, Xianghu Yue, Chen Zhang, Xiaoxue Gao, Robby T Tan, and Haizhou Li. 2024b. Voicebench: Benchmarking llm-based voice assistants. arXiv preprint arXiv:2410.17196.
  10. Yunfei Chu, Jin Xu, Qian Yang, Haojie Wei, Xipin Wei, Zhifang Guo, Yichong Leng, Yuanjun Lv, Jinzheng He, Junyang Lin, Chang Zhou, and Jingren Zhou. 2024. Qwen2-audio technical report. arXiv preprint arXiv:2407.10759.
  11. Yunfei Chu, Jin Xu, Xiaohuan Zhou, Qian Yang, Shiliang Zhang, Zhijie Yan, Chang Zhou, and Jingren Zhou. 2023. Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models. arXiv preprint arXiv:2311.07919.
  12. Michaël Defferrard, Kirell Benzi, Pierre Vandergheynst, and Xavier Bresson. 2016. Fma: A dataset for music analysis. Preprint, arXiv:1612.01840. — [arXiv:1612.01840](https://arxiv.org/abs/1612.01840) find
  13. Alexandre Défossez, Laurent Mazaré, Manu Orsini, Amélie Royer, Patrick Pérez, Hervé Jégou, Edouard Grave, and Neil Zeghidour. 2024. Moshi: a speech-text foundation model for real-time dialogue. arXiv preprint arXiv:2410.00037.
  14. Ding Ding, Zeqian Ju, Yichong Leng, Songxiang Liu, Tong Liu, Zeyu Shang, Kai Shen, Wei Song, Xu Tan, Heyi Tang, and 1 others. 2025. Kimi-audio technical report. arXiv preprint arXiv:2504.18425.
  15. Anuj Diwan, Zhisheng Zheng, David Harwath, and Eunsol Choi. 2025. Scaling rich style-prompted text-to-speech datasets. Preprint, arXiv:2503.04713. find
  16. Seungheon Doh, Keunwoo Choi, Jongpil Lee, and Juhan Nam. 2023. Lp-musiccaps: Llm-based pseudo music captioning. In Ismir 2023 Hybrid Conference. find
  17. Konstantinos Drossos, Samuel Lipping, and Tuomas Virtanen. 2019. Clotho: An audio captioning dataset. Preprint, arXiv:1910.09387. — [arXiv:1910.09387](https://arxiv.org/abs/1910.09387) find
  18. Zhihao Du, Yuxuan Wang, Qian Chen, Xian Shi, Xiang Lv, Tianyu Zhao, Zhifu Gao, Yexin Yang, Changfeng Gao, Hui Wang, and 1 others. 2024. Cosyvoice 2: Scalable streaming speech synthesis with large language models. arXiv preprint arXiv:2412.10117.
  19. Jesse Engel, Cinjon Resnick, Adam Roberts, Sander Dieleman, Douglas Eck, Karen Simonyan, and Mohammad Norouzi. 2017. Neural audio synthesis of musical notes with wavenet autoencoders. Preprint, arXiv:1704.01279. — [arXiv:1704.01279](https://arxiv.org/abs/1704.01279) find
  20. Qingkai Fang, Shoutao Guo, Yan Zhou, Zhengrui Ma, Shaolei Zhang, and Yang Feng. 2025. LLaMA-omni: Seamless speech interaction with large language models. In The Thirteenth International Conference on Learning Representations.
  21. Chaoyou Fu, Haojia Lin, Zuwei Long, Yunhang Shen, Yuhang Dai, Meng Zhao, Yi-Fan Zhang, Shaoqi Dong, Yangze Li, Xiong Wang, and 1 others. 2024. Vita: Towards open-source interactive omni multimodal llm. arXiv preprint arXiv:2408.05211. — [arXiv:2408.05211](https://arxiv.org/abs/2408.05211) find
  22. Sreyan Ghosh, Zhifeng Kong, Sonal Kumar, S Sakshi, Jaehyeon Kim, Wei Ping, Rafael Valle, Dinesh Manocha, and Bryan Catanzaro. 2025. Audio flamingo 2: An audio-language model with long-audio understanding and expert reasoning abilities. In Forty-second International Conference on Machine Learning. find
  23. Sreyan Ghosh, Sonal Kumar, Ashish Seth, Chandra Kiran Reddy Evuru, Utkarsh Tyagi, S Sakshi, Oriol Nieto, Ramani Duraiswami, and Dinesh Manocha. 2024. Gama: A large audio-language model with advanced audio understanding and complex reasoning abilities. arXiv preprint arXiv:2406.11768.
  24. Yuan Gong, Hongyin Luo, Alexander H. Liu, Leonid Karlinsky, and James R. Glass. 2024. Listen, think, and understand. In The Twelfth International Conference on Learning Representations. find
  25. Yuan Gong, Jin Yu, and James Glass. 2022. Vocalsound: A dataset for improving human vocal sounds recognition. Preprint, arXiv:2205.03433. — [arXiv:2205.03433](https://arxiv.org/abs/2205.03433) find
  26. Haolin He, Xingjian Du, Renhe Sun, Zheqi Dai, Yujia Xiao, Mingru Yang, Jiayi Zhou, Xiquan Li, Zhengxi Liu, Zining Liang, and 1 others. 2025. Measuring audio’s impact on correctness: Audio-contribution-aware post-training of large audio language models. arXiv preprint arXiv:2509.21060. — [arXiv:2509.21060](https://arxiv.org/abs/2509.21060) find
  27. William Held, Ella Li, Michael Ryan, Weiyan Shi, Yanzhe Zhang, and Diyi Yang. 2024. Distilling an end-to-end voice assistant without instruction training data. arXiv preprint arXiv:2410.02678.
  28. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, and 1 others. 2022. Lora: Low-rank adaptation of large language models. ICLR, 1(2):3.
  29. Ailin Huang, Boyong Wu, Bruce Wang, Chao Yan, Chen Hu, Chengli Feng, Fei Tian, Feiyu Shen, Jingbei Li, Mingrui Chen, and 1 others. 2025. Step-audio: Unified understanding and generation in intelligent speech interaction. arXiv preprint arXiv:2502.11946.
  30. Zeyu Jin, Jia Jia, Qixin Wang, Kehan Li, Shuoyi Zhou, Songtao Zhou, Xiaoyu Qin, and Zhiyong Wu. 2024. Speechcraft: A fine-grained expressive speech dataset with natural language description. In Proceedings of the 32nd ACM International Conference on Multimedia, pages 1255–1264. find
  31. Mandar Joshi, Eunsol Choi, Daniel S Weld, and Luke Zettlemoyer. 2017. Triviaqa: A large scale distantly supervised challenge dataset for reading comprehension. arXiv preprint arXiv:1705.03551.
  32. Chris Dongjoo Kim, Byeongchang Kim, Hyunmin Lee, and Gunhee Kim. 2019. Audiocaps: Generating captions for audios in the wild. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1, pages 119– 132. A…
  33. Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, and 1 others. 2019. Natural questions: a benchmark for question answering research. Transactions of the Association for Computational Lin…
  34. Jinsong Li, Xiaoyi Dong, Yuhang Zang, Yuhang Cao, Jiaqi Wang, and Dahua Lin. 2025a. Beyond fixed: Training-free variable-length denoising for diffusion large language models. arXiv preprint arXiv:2508.00819. — [arXiv:2508.00819](https://arxiv.org/abs/2508.00819) find
  35. Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning, pages 19730–19742. PMLR.
  36. Tianpeng Li, Jun Liu, Tao Zhang, Yuanbo Fang, Da Pan, Mingrui Wang, Zheng Liang, Zehuan Li, Mingan Lin, Guosheng Dong, and 1 others. 2025b. Baichuan-audio: A unified framework for end-to-end speech interaction. arXiv preprint arXiv:2502.17239.
  37. Yadong Li, Haoze Sun, Mingan Lin, Tianpeng Li, Guosheng Dong, Tao Zhang, Bowen Ding, Wei Song, Zhenglin Cheng, Yuqi Huo, and 1 others. 2024. Baichuan-omni technical report. arXiv preprint arXiv:2410.08565.
  38. Ke-Han Lu, Zhehuai Chen, Szu-Wei Fu, and Chao-Han Huck Yang et al. 2025. Desta2.5-audio: Toward general-purpose large audio language model with self-generated cross-modal alignment. Preprint, arXiv:2507.02768. — [arXiv:2507.02768](https://arxiv.org/abs/2507.02768) find
  39. Ziyang Ma, Yinghao Ma, Yanqiao Zhu, Chen Yang, Yi-Wen Chao, Ruiyang Xu, Wenxi Chen, Yuanzhe Chen, Zhuo Chen, Jian Cong, Kai Li, Keliang Li, Siyou Li, Xinfeng Li, Xiquan Li, Zheng Lian, Yuzhe Liang, Minghao Liu, Zhikang Niu, and 15 others. 2025. MMAR: A challenging benchmark for deep reasoning in spe… find
  40. Xinhao Mei, Chutong Meng, Haohe Liu, Qiuqiang Kong, Tom Ko, Chengqi Zhao, Mark D. Plumbley, Yuexian Zou, and Wenwu Wang. 2023. Wavcaps: A chatgpt-assisted weakly-labelled audio captioning dataset for audio-language multimodal research. Preprint, arXiv:2303.17395. find
  41. Arsha Nagrani, Joon Son Chung, and Andrew Zisserman. 2017. Voxceleb: a large-scale speaker identification dataset. In Interspeech 2017. find
  42. Jinjie Ni, Qian Liu, Longxu Dou, Chao Du, Zili Wang, Hang Yan, Tianyu Pang, and Michael Qizhe Shieh. 2025. Diffusion language models are super data learners. arXiv preprint arXiv:2511.03276. — [arXiv:2511.03276](https://arxiv.org/abs/2511.03276) find
  43. Shen Nie, Fengqi Zhu, Zebin You, Xiaolu Zhang, Jingyang Ou, Jun Hu, JUN ZHOU, Yankai Lin, Ji-Rong Wen, and Chongxuan Li. 2025. Large language diffusion models. In The Thirty-ninth Annual Conference on Neural Information Processing Systems.
  44. OpenAI, :, Aaron Hurst, Adam Lerer, Adam P. Goucher, and Adam Perelman et al. 2024. Gpt-4o system card. Preprint, arXiv:2410.21276.
  45. Jingyang Ou, Shen Nie, Kaiwen Xue, Fengqi Zhu, Jiacheng Sun, Zhenguo Li, and Chongxuan Li. 2025. Your absorbing discrete diffusion secretly models the conditional distributions of clean data. In The Thirteenth International Conference on Learning Representations. find
  46. Vassil Panayotov, Guoguo Chen, Daniel Povey, and Sanjeev Khudanpur. 2015. Librispeech: an asr corpus based on public domain audio books. In 2015 IEEE international conference on acoustics, speech and signal processing (ICASSP), pages 5206–5210. IEEE. find
  47. Karol J. Piczak. 2015. Esc: Dataset for environmental sound classification. In Proceedings of the 23rd Annual ACM Conference on Multimedia, pages 1015– 1018. ACM Press. find
  48. Soujanya Poria, Devamanyu Hazarika, Navonil Majumder, Gautam Naik, Erik Cambria, and Rada Mihalcea. 2019. Meld: A multimodal multi-party dataset for emotion recognition in conversations. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 527–536. Associ…
  49. Paul Primus, Florian Schmid, and Gerhard Widmer. 2025. Tacos: Temporally-aligned audio captions for language-audio pretraining. arXiv preprint arXiv:2505.07609. — [arXiv:2505.07609](https://arxiv.org/abs/2505.07609) find
  50. Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. 2023. Robust speech recognition via large-scale weak supervision. In International conference on machine learning, pages 28492–28518. PMLR.
  51. Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2023. Direct preference optimization: Your language model is secretly a reward model. Advances in neural information processing systems, 36:53728–53741.
  52. Subham Sekhar Sahoo, Marianne Arriola, Yair Schiff, Aaron Gokaslan, Edgar Marroquin, Justin T Chiu, Alexander Rush, and Volodymyr Kuleshov. 2024. Simple and effective masked diffusion language models. ArXiv, abs/2406.07524.
  53. S Sakshi, Utkarsh Tyagi, Sonal Kumar, Ashish Seth, Ramaneswaran Selvakumar, Oriol Nieto, Ramani Duraiswami, Sreyan Ghosh, and Dinesh Manocha. 2025. MMAU: A massive multi-task audio understanding and reasoning benchmark. In The Thirteenth International Conference on Learning Representations.
  54. Jiaxin Shi, Kehang Han, Zhe Wang, Arnaud Doucet, and Michalis Titsias. 2024. Simplified and generalized masked diffusion for discrete data. Advances in neural information processing systems, 37:103131– 103167.
  55. Changli Tang, Wenyi Yu, Guangzhi Sun, Xianzhao Chen, Tian Tan, Wei Li, Lu Lu, Zejun MA, and Chao Zhang. 2024a. SALMONN: Towards generic hearing abilities for large language models. In The Twelfth International Conference on Learning Representations.
  56. Changli Tang, Wenyi Yu, Guangzhi Sun, Xianzhao Chen, Tian Tan, Wei Li, Lu Lu, Zejun Ma, and Chao Zhang. 2024b. Salmonn: Towards generic hearing abilities for large language models. In ICLR.
  57. Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, Xuechen Li, Carlos Guestrin, Percy Liang, and Tatsunori B. Hashimoto. 2023. Stanford alpaca: An instruction-following llama model. https://gi thub.com/tatsu-lab/stanford_alpaca. find
  58. Gemini Team, Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, and et al. 2025. Gemini: A family of highly capable multimodal models. Preprint, arXiv:2312.11805.
  59. OpenBMB MiniCPM-o Team. 2025. Minicpm-o 2.6: A gpt-4o level mllm for vision, speech, and multimodal live streaming on your phone. find
  60. Irina-Elena Veliche, Zhuangqun Huang, Vineeth Ayyat Kochaniyan, Fuchun Peng, Ozlem Kalinli, and Michael L. Seltzer. 2024. Towards measuring fairness in speech recognition: Fair-Speech dataset. In Interspeech 2024, pages 1385–1389. find
  61. Chen Wang, Tianyu Peng, Wen Yang, Yinan Bai, Guangfu Wang, Jun Lin, Lanpeng Jia, Lingxiang Wu, Jinqiao Wang, Chengqing Zong, and 1 others. 2025a. Opens2s: Advancing fully open-source end-to-end empathetic large speech language model. In Proceedings of the 2025 Conference on Empirical Methods in Natu… find
  62. Dingdong Wang, Jincenzi Wu, Junan Li, Dongchao Yang, Xueyuan Chen, Tianhua Zhang, and Helen Meng. 2025b. Mmsu: A massive multi-task spoken language understanding and reasoning benchmark. arXiv preprint arXiv:2506.04779. — [arXiv:2506.04779](https://arxiv.org/abs/2506.04779) find
  63. Xiong Wang, Yangze Li, Chaoyou Fu, Yike Zhang, Yunhang Shen, Lei Xie, Ke Li, Xing Sun, and Long MA. 2025c. Freeze-omni: A smart and low latency speech-to-speech dialogue model with frozen LLM. In Forty-second International Conference on Machine Learning. find
  64. Linye Wei, Wenjue Chen, Pingzhi Tang, Xiaotian Guo, Le Ye, Runsheng Wang, and Meng Li. 2025. Orchestrating dual-boundaries: An arithmetic intensity inspired acceleration framework for diffusion language models. Preprint, arXiv:2511.21759. — [arXiv:2511.21759](https://arxiv.org/abs/2511.21759) find
  65. Chengyue Wu, Hao Zhang, Shuchen Xue, Zhijian Liu, Shizhe Diao, Ligeng Zhu, Ping Luo, Song Han, and Enze Xie. 2025. Fast-dllm: Training-free acceleration of diffusion llm by enabling kv cache and parallel decoding. Preprint, arXiv:2505.22618. — [arXiv:2505.22618](https://arxiv.org/abs/2505.22618) find
  66. Zhifei Xie and Changqiao Wu. 2024a. Mini-omni: Language models can hear, talk while thinking in streaming. arXiv preprint arXiv:2408.16725.
  67. Zhifei Xie and Changqiao Wu. 2024b. Mini-omni2: Towards open-source gpt-4o with vision, speech and duplex capabilities. arXiv preprint arXiv:2410.11190. — [arXiv:2410.11190](https://arxiv.org/abs/2410.11190) find
  68. Jin Xu, Zhifang Guo, Jinzheng He, Hangrui Hu, Ting He, Shuai Bai, Keqin Chen, Jialin Wang, Yang Fan, Kai Dang, and 1 others. 2025a. Qwen2. 5-omni technical report. arXiv preprint arXiv:2503.20215. — Qwen2.5-Omni Technical Report
  69. Jin Xu, Zhifang Guo, Hangrui Hu, Yunfei Chu, Xiong Wang, Jinzheng He, Yuxuan Wang, Xian Shi, Ting He, Xinfa Zhu, Yuanjun Lv, Yongqi Wang, Dake Guo, He Wang, Linhan Ma, Pei Zhang, Xinyu Zhang, Hongkun Hao, Zishan Guo, and 19 others. 2025b. Qwen3-omni technical report. arXiv preprint arXiv:2509.17765.
  70. Junichi Yamagishi, Christophe Veaux, and Kirsten Mac-Donald. 2019. Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit. Dataset from University of Edinburgh. find
  71. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, and 1 others. 2025. Qwen3 technical report. arXiv preprint arXiv:2505.09388.
  72. Aohan Zeng, Zhengxiao Du, Mingdao Liu, Kedong Wang, Shengmin Jiang, Lei Zhao, Yuxiao Dong, and Jie Tang. 2024. Glm-4-voice: Towards intelligent and human-like end-to-end spoken chatbot. arXiv preprint arXiv:2412.02612.
  73. Dong Zhang, Shimin Li, Xin Zhang, Jun Zhan, Pengyu Wang, Yaqian Zhou, and Xipeng Qiu. 2023. Speechgpt: Empowering large language models with intrinsic cross-modal conversational abilities. arXiv preprint arXiv:2305.11000.
  74. Jiaming Zhou, Hongjie Chen, Shiwan Zhao, Jian Kang, Jie Li, Enzhi Wang, Yujie Guo, Haoqin Sun, Hui Wang, Aobo Kong, and 1 others. 2025. Diffa: Large language diffusion models can listen and understand. arXiv preprint arXiv:2507.18452. — [arXiv:2507.18452](https://arxiv.org/abs/2507.18452) find
  75. Fengqi Zhu, Rongzhen Wang, Shen Nie, Xiaolu Zhang, Chunwei Wu, Jun Hu, Jun Zhou, Jianfei Chen, Yankai Lin, Ji-Rong Wen, and Chongxuan Li. 2025. Llada 1.5: Variance-reduced preference optimization for large language diffusion models. Preprint, arXiv:2505.19223.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/zhou-2026-diffa-2-practical-diffusion-large/