Elamur Research
☰
home / papers / 2025 / Qwen3-Omni Technical Report

Qwen3-Omni Technical Report

Written for the Research library (claude-opus-5-5) from the paper text. Original — arxiv.org/pdf/2509.17765

Summary

Multimodal LLMs often lose ground in one modality when they gain in another. The Qwen Team built Qwen3-Omni, a single end-to-end model that handles text, images, audio and video and responds with text or streaming speech. It does this without falling below same-sized single-modality Qwen models. The model extends the Thinker–Talker design of Qwen2.5-Omni. Both parts become Mixture-of-Experts, and Whisper is replaced by a new AuT audio encoder trained from scratch. The Talker predicts multi-codebook speech codecs, and a light causal ConvNet turns them into audio frame by frame. The authors credit parity across modalities mainly to blending unimodal and cross-modal data early in text pretraining. The release also includes a reasoning-focused Thinking variant and an audio Captioner, since no general-purpose audio captioning model was available to researchers. Qwen3-Omni shows especially strong results on audio and audio-visual tasks, where it beats several closed systems. Because the weights are open, it is a practical base for multilingual speech and multimodal work.

Key points

  • On 36 audio and audio-visual benchmarks, the model is the best open-source system on 32 and the best overall on 22. It surpasses Gemini-2.5-Pro, Seed-ASR and GPT-4o-Transcribe.
  • AuT (Audio Transformer) has about 0.6B parameters and was trained on 20 million hours of supervised audio, produces tokens at 12.5 Hz, and uses dynamic attention windows of 1–8 s. The vision encoder comes from Qwen3-VL and is initialized from SigLIP2-So400m (about 543M parameters).
  • Language coverage is 119 languages for text, 19 for speech understanding and 10 for speech generation. The model can take audio inputs of up to 40 minutes for ASR and spoken-language understanding.
  • Speech generation uses MTP modules to predict residual codebooks, and Code2Wav swaps block-wise DiT for a causal ConvNet. Together these give a theoretical cold-start first-packet latency of 234 ms.
  • Qwen3-Omni-30B-A3B, -Thinking and -Captioner are released under the Apache 2.0 license.

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

Fields: Natural language processing

Cited by

111 papers of our library cite it (of the 140673 whose bibliographies we read).

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2509.17765 · arXiv 2509.17765

@misc{xu2025qwen3,
  title = {{Qwen3-Omni Technical Report}},
  author = {Xu, Jin and Guo, Zhifang and Hu, Hangrui and Chu, Yunfei and Wang, Xiong and He, Jinzheng and Wang, Yuxuan and Shi, Xian and He, Ting and Zhu, Xinfa and Lv, Yuanjun and Wang, Yongqi and Guo, Dake and Wang, He and Ma, Linhan and Zhang, Pei and Zhang, Xinyu and Hao, Hongkun and Guo, Zishan and Yang, Baosong and Zhang, Bin and Ma, Ziyang and Wei, Xipin and Bai, Shuai and Chen, Keqin and Liu, Xuejing and Wang, Peng and Yang, Mingkun and Liu, Dayiheng and Ren, Xingzhang and Zheng, Bo and Men, Rui and Zhou, Fan and Yu, Bowen and Yang, Jianxin and Yu, Le and Zhou, Jingren and Lin, Junyang},
  year = {2025},
  doi = {10.48550/arxiv.2509.17765},
  eprint = {2509.17765},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2509.17765}
}

References

75 references, 24 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Pravesh Agrawal, Szymon Antoniak, Emma Bou Hanna, Baptiste Bout, Devendra Chaplot, Jessica Chudnovsky, Diogo Costa, Baudouin De Monicault, Saurabh Garg, Theophile Gervet, Soham Ghosh, Amélie Héliou, Paul Jacob, Albert Q. Jiang, Kartik Khandelwal, Timothée Lacroix, Guillaume Lample, Diego Las Casas,… find
  2. AIME. AIME problems and solutions, 2025. URL https://artofproblemsolving.com/wiki/index.php/A IME\_Problems\_and\_Solutions. ↗
  3. Philip Anastassiou, Jiawei Chen, Jitong Chen, Yuanzhe Chen, Zhuo Chen, Ziyi Chen, Jian Cong, Lelai Deng, Chuang Ding, Lu Gao, et al. Seed-tts: A family of high-quality versatile speech generation models. arXiv preprint arXiv:2406.02430, 2024. find
  4. Anthropic. Introducing Claude, 2023a. URL https://www.anthropic.com/index/introducing-claude. ↗
  5. Anthropic. Claude 2. Technical report, Anthropic, 2023b. URL https://www-files.anthropic.com/pro duction/images/Model-Card-Claude-2.pdf. ↗
  6. Anthropic. The Claude 3 model family: Opus, Sonnet, Haiku. Technical report, Anthropic, AI, 2024. URL https://www-cdn.anthropic.com/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627/Model\_Card\_Claude\_ 3.pdf. ↗
  7. Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, Binyuan Hui, Luo Ji, Mei Li, Junyang Lin, Runji Lin, Dayiheng Liu, Gao Liu, Chengqiang Lu, Keming Lu, Jianxin Ma, Rui Men, Xingzhang Ren, Xuancheng Ren, Chuanqi Tan, Sinan Tan, Jianhong Tu, P… find our card
  8. Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. Qwen-VL: A frontier large vision-language model with versatile abilities. CoRR, abs/2308.12966, 2023b. find our card
  9. Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, et al. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923, 2025. find our card
  10. Dmitry Bogdanov, Minz Won, Philip Tovstogan, Alastair Porter, and Xavier Serra. The mtg-jamendo dataset for automatic music tagging. ICML, 2019. find
  11. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. Language models are few-shot learners. In NeurIPS, 2020. find
  12. Federico Cassano, John Gouwar, Daniel Nguyen, Sydney Nguyen, Luna Phipps-Costin, Donald Pinckney, Ming-Ho Yee, Yangtian Zi, Carolyn Jane Anderson, Molly Q. Feldman, Arjun Guha, Michael Greenberg, and Abhinav Jangda. MultiPL-E: A scalable and polyglot approach to benchmarking neural code generation.… find
  13. Lin Chen, Jinsong Li, Xiaoyi Dong, Pan Zhang, Yuhang Zang, Zehui Chen, Haodong Duan, Jiaqi Wang, Yu Qiao, Dahua Lin, et al. Are we on the right way for evaluating large vision-language models? arXiv:2403.20330, 2024a. find our card
  14. Yiming Chen, Xianghu Yue, Chen Zhang, Xiaoxue Gao, Robby T Tan, and Haizhou Li. Voicebench: Benchmarking llm-based voice assistants. arXiv preprint arXiv:2410.17196, 2024b. find
  15. Yushen Chen, Zhikang Niu, Ziyang Ma, Keqi Deng, Chunhui Wang, Jian Zhao, Kai Yu, and Xie Chen. F5-tts: A fairytaler that fakes fluent and faithful speech with flow matching. arXiv preprint arXiv:2410.06885, 2024c. find
  16. Junhao Cheng, Yuying Ge, Teng Wang, Yixiao Ge, Jing Liao, and Ying Shan. Video-holmes: Can MLLM think like holmes for complex video reasoning? CoRR, abs/2505.21374, 2025. — [arXiv:2505.21374](https://arxiv.org/abs/2505.21374) find
  17. Yunfei Chu, Jin Xu, Xiaohuan Zhou, Qian Yang, Shiliang Zhang, Zhijie Yan, Chang Zhou, and Jingren Zhou. Qwen-Audio: Advancing universal audio understanding via unified large-scale audio-language models. CoRR, abs/2311.07919, 2023. find our card
  18. Yunfei Chu, Jin Xu, Qian Yang, Haojie Wei, Xipin Wei, Zhifang Guo, Yichong Leng, Yuanjun Lv, Jinzheng He, Junyang Lin, et al. Qwen2-audio technical report. arXiv preprint arXiv:2407.10759, 2024. find our card
  19. Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, et al. Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arXiv preprint a… find our card
  20. Zhihao Du, Yuxuan Wang, Qian Chen, Xian Shi, Xiang Lv, Tianyu Zhao, Zhifu Gao, Yexin Yang, Changfeng Gao, Hui Wang, et al. Cosyvoice 2: Scalable streaming speech synthesis with large language models. arXiv preprint arXiv:2412.10117, 2024. find
  21. Zhihao Du, Changfeng Gao, Yuxuan Wang, Fan Yu, Tianyu Zhao, Hao Wang, Xiang Lv, Hui Wang, Chongjia Ni, Xian Shi, Keyu An, Guanrou Yang, Yabin Li, Yanni Chen, Zhifu Gao, Qian Chen, Yue Gu, Mengzhe Chen, Yafeng Chen, Shiliang Zhang, Wen Wang, and Jieping Ye. Cosyvoice 3: Towards in-the-wild speech gen… — [arXiv:2505.17589](https://arxiv.org/abs/2505.17589) find
  22. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, Arun Rao, Aston Zhang, Aurélien Rodriguez,… find
  23. Sefik Emre Eskimez, Xiaofei Wang, Manthan Thakker, Canrun Li, Chung-Hsien Tsai, Zhen Xiao, Hemin Yang, Zirun Zhu, Min Tang, Xu Tan, et al. E2 tts: Embarrassingly easy fully non-autoregressive zero-shot tts. In 2024 IEEE Spoken Language Technology Workshop (SLT), pp. 682–689. find
  24. Chaoyou Fu, Yuhan Dai, Yondong Luo, Lei Li, Shuhuai Ren, Renrui Zhang, Zihan Wang, Chenyu Zhou, Yunhang Shen, Mengdan Zhang, et al. Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal llms in video analysis. arXiv:2405.21075, 2024. find our card
  25. Aryo Pradipta Gema, Joshua Ong Jun Leang, Giwon Hong, Alessio Devoto, Alberto Carlo Maria Mancino, Rohit Saxena, Xuanli He, Yu Zhao, Xiaotang Du, Mohammad Reza Ghasemi Madani, et al. Are we done with mmlu? CoRR, abs/2406.04127, 2024. find
  26. Gemini Team. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. Technical report, Google, 2024. URL https://storage.googleapis.com/deepmind-media/gemini/gemi ni\_v1\_5\_report.pdf. ↗ our card
  27. Arushi Goel, Sreyan Ghosh, Jaehyeon Kim, Sonal Kumar, Zhifeng Kong, Sang-gil Lee, Chao-Han Huck Yang, Ramani Duraiswami, Dinesh Manocha, Rafael Valle, et al. Audio flamingo 3: Advancing audio intelligence with fully open large audio language models. arXiv preprint arXiv:2507.08128, 2025. — [arXiv:2507.08128](https://arxiv.org/abs/2507.08128) find
  28. Tianrui Guan, Fuxiao Liu, Xiyang Wu, Ruiqi Xian, Zongxia Li, Xiaoyu Liu, Xijun Wang, Lichang Chen, Furong Huang, Yaser Yacoob, Dinesh Manocha, and Tianyi Zhou. Hallusionbench: An advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-language models. In IE… find our card
  29. Yun He, Di Jin, Chaoqi Wang, Chloe Bi, Karishma Mandyam, Hejia Zhang, Chen Zhu, Ning Li, Tengyu Xu, Hongjiang Lv, Shruti Bhosale, Chenguang Zhu, Karthik Abinav Sankararaman, Eryk Helenowski, Melanie Kambadur, Aditya Tayade, Hao Ma, Han Fang, and Sinong Wang. Multi-if: Benchmarking llms on multi-turn… — [doi:10.48550/arxiv.2410.15553](https://doi.org/10.48550/arxiv.2410.15553) find
  30. Jack Hong, Shilin Yan, Jiayin Cai, Xiaolong Jiang, Yao Hu, and Weidi Xie. Worldsense: Evaluating real-world omnimodal understanding for multimodal llms. CoRR, abs/2502.04326, 2025. — [arXiv:2502.04326](https://arxiv.org/abs/2502.04326) find
  31. Aniruddha Kembhavi, Mike Salvato, Eric Kolve, Minjoon Seo, Hannaneh Hajishirzi, and Ali Farhadi. A diagram is worth a dozen images. In ECCV, 2016. find our card
  32. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, and Ion Stoica. Efficient memory management for large language model serving with pagedattention. In Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles, 2023. find
  33. Edith Law, Kris West, Michael I Mandel, Mert Bay, and J Stephen Downie. Evaluation of algorithms using games: The case of music tagging. In ISMIR, pp. 387–392, 2009. find
  34. Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv:2301.12597, 2023. find our card
  35. Bill Yuchen Lin, Ronan Le Bras, Kyle Richardson, Ashish Sabharwal, Radha Poovendran, Peter Clark, and Yejin Choi. ZebraLogic: On the scaling limits of LLMs for logical reasoning. CoRR, abs/2502.01100, 2025. find
  36. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. Visual instruction tuning. arXiv:2304.08485, 2023. find our card
  37. Pan Lu, Hritik Bansal, Tony Xia, Jiacheng Liu, Chunyuan Li, Hannaneh Hajishirzi, Hao Cheng, Kai-Wei Chang, Michel Galley, and Jianfeng Gao. Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts. In ICLR, 2024. find our card
  38. Ahmed Masry, Do Xuan Long, Jia Qing Tan, Shafiq Joty, and Enamul Hoque. Chartqa: A benchmark for question answering about charts with visual and logical reasoning. arXiv:2203.10244, 2022. find our card
  39. OpenAI. ChatML, 2022. URL https://github.com/openai/openai-python/blob/e389823ba013a24b4c3 2ce38fa0bd87e6bccae94/chatml.md. ↗
  40. OpenAI. GPT4 technical report. CoRR, abs/2303.08774, 2023. find our card
  41. OpenAI. Hello GPT-4o, 2024. URL https://openai.com/index/hello-gpt-4o/. ↗
  42. Samuel J. Paech. Creative writing v3, 2024. URL https://eqbench.com/creative\_writing.html. ↗
  43. Roni Paiss, Ariel Ephrat, Omer Tov, Shiran Zada, Inbar Mosseri, Michal Irani, and Tali Dekel. Teaching CLIP to count to ten. In IEEE/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1-6, 2023, pp. 3147–3157. find
  44. Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D. Manning, Stefano Ermon, and Chelsea Finn. Direct preference optimization: Your language model is secretly a reward model. In NeurIPS, 2023. find
  45. David Rein, Betty Li Hou, Asa Cooper Stickland, Jackson Petty, Richard Yuanzhe Pang, Julien Dirani, Julian Michael, and Samuel R. Bowman. GPQA: A graduate-level Google-proof Q&A benchmark. CoRR, abs/2311.12022, 2023. find our card
  46. S Sakshi, Utkarsh Tyagi, Sonal Kumar, Ashish Seth, Ramaneswaran Selvakumar, Oriol Nieto, Ramani Duraiswami, Sreyan Ghosh, and Dinesh Manocha. Mmau: A massive multi-task audio understanding and reasoning benchmark, 2024. URL https://arxiv.org/abs/2410.19168. ↗
  47. Jianlin Su, Murtadha H. M. Ahmed, Yu Lu, Shengfeng Pan, Wen Bo, and Yunfeng Liu. Roformer: Enhanced Transformer with rotary position embedding. Neurocomputing, 568:127063, 2024. find
  48. Changli Tang, Yixuan Li, Yudong Yang, Jimin Zhuang, Guangzhi Sun, Wei Li, Zejun Ma, and Chao Zhang. video-salmonn 2: Captioning-enhanced audio-visual large language models. CoRR, abs/2506.15220, 2025. — [arXiv:2506.15220](https://arxiv.org/abs/2506.15220) find
  49. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. Llama 2: Open foundation and fine-tuned chat models. arXiv:2307.09288, 2023. find
  50. Michael Tschannen, Alexey Gritsenko, Xiao Wang, Muhammad Ferjad Naeem, Ibrahim Alabdulmohsin, Nikhil Parthasarathy, Talfan Evans, Lucas Beyer, Ye Xia, Basil Mustafa, Olivier Hénaff, Jeremiah Harmsen, Andreas Steiner, and Xiaohua Zhai. Siglip 2: Multilingual vision-language encoders with improved sem… find
  51. George Tzanetakis and Perry Cook. Musical genre classification of audio signals. IEEE Transactions on speech and audio processing, 10(5):293–302, 2002. find
  52. Dingdong Wang, Jincenzi Wu, Junan Li, Dongchao Yang, Xueyuan Chen, Tianhua Zhang, and Helen Meng. MMSU: A massive multi-task spoken language understanding and reasoning benchmark. CoRR, abs/2506.04779, 2025a. doi: 10.48550/ARXIV.2506.04779. URL https://doi.org/10.48550/arXiv.250 6.04779. — [doi:10.48550/arxiv.2506.04779](https://doi.org/10.48550/arxiv.2506.04779) ↗
  53. Ke Wang, Junting Pan, Weikang Shi, Zimu Lu, Mingjie Zhan, and Hongsheng Li. Measuring multimodal mathematical reasoning with math-vision dataset. arXiv:2402.14804, 2024a. find our card
  54. Weihan Wang, Zehai He, Wenyi Hong, Yean Cheng, Xiaohan Zhang, Ji Qi, Shiyu Huang, Bin Xu, Yuxiao Dong, Ming Ding, and Jie Tang. Lvbench: An extreme long video understanding benchmark. CoRR, abs/2406.08035, 2024b. find
  55. Xinsheng Wang, Mingqi Jiang, Ziyang Ma, Ziyu Zhang, Songxiang Liu, Linqin Li, Zheng Liang, Qixi Zheng, Rui Wang, Xiaoqin Feng, Weizhen Bian, Zhen Ye, Sitong Cheng, Ruibin Yuan, Zhixian Zhao, Xinfa Zhu, Jiahao Pan, Liumeng Xue, Pengcheng Zhu, Yunlin Chen, Zhifei Li, Xie Chen, Lei Xie, Yike Guo, and W… — [arXiv:2503.01710](https://arxiv.org/abs/2503.01710) find
  56. Yiming Wang, Pei Zhang, Jialong Tang, Haoran Wei, Baosong Yang, Rui Wang, Chenshu Sun, Feitong Sun, Jiran Zhang, Junxuan Wu, Qiqian Cang, Yichang Zhang, Fei Huang, Junyang Lin, Fei Huang, and Jingren Zhou. Polymath: Evaluating mathematical reasoning in multilingual contexts. CoRR, abs/2504.18428, 20… — [doi:10.48550/arxiv.2504.18428](https://doi.org/10.48550/arxiv.2504.18428) find
  57. Yuancheng Wang, Haoyue Zhan, Liwei Liu, Ruihong Zeng, Haotian Guo, Jiachen Zheng, Qiang Zhang, Xueyao Zhang, Shunsi Zhang, and Zhizheng Wu. Maskgct: Zero-shot text-to-speech with masked generative codec transformer. arXiv preprint arXiv:2409.00750, 2024c. — [arXiv:2409.00750](https://arxiv.org/abs/2409.00750) find
  58. Shangda Wu, Zhancheng Guo, Ruibin Yuan, Junyan Jiang, Seungheon Doh, Gus Xia, Juhan Nam, Xiaobing Li, Feng Yu, and Maosong Sun. Clamp 3: Universal music information retrieval across unaligned modalities and unseen languages. arXiv preprint arXiv:2502.10362, 2025a. find
  59. Yuning Wu, Jiahao Mei, Ming Yan, Chenliang Li, Shaopeng Lai, Yuran Ren, Zijia Wang, Ji Zhang, Mengyue Wu, Qin Jin, and Fei Huang. WritingBench: A comprehensive benchmark for generative writing. CoRR, abs/2503.05244, 2025b. — [arXiv:2503.05244](https://arxiv.org/abs/2503.05244) find
  60. Jin Xu, Zhifang Guo, Jinzheng He, Hangrui Hu, Ting He, Shuai Bai, Keqin Chen, Jialin Wang, Yang Fan, Kai Dang, et al. Qwen2. 5-omni technical report. arXiv preprint arXiv:2503.20215, 2025. find our card
  61. Fanjia Yan, Huanzhi Mao, Charlie Cheng-Jie Ji, Tianjun Zhang, Shishir G. Patil, Ion Stoica, and Joseph E. Gonzalez. Berkeley function calling leaderboard. https://gorilla.cs.berkeley.edu/blogs/8\_berkel ey\_function\_calling\_leaderboard.html, 2024. ↗
  62. An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, et al. Qwen2 technical report. arXiv:2407.10671, 2024. find
  63. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, et al. Qwen3 technical report. arXiv preprint arXiv:2505.09388, 2025a. find our card
  64. Qize Yang, Shimin Yao, Weixuan chen, Shenghao Fu, Detao Bai, Jiaxing Zhao, Boyuan Sun, Bowen Yin, Xihan Wei, and Jingren Zhou. Humanomniv2: From understanding to omni-modal reasoning with context. CoRR, abs/2506.21277, 2025b. — [arXiv:2506.21277](https://arxiv.org/abs/2506.21277) find
  65. Ruibin Yuan, Yinghao Ma, Yizhi Li, Ge Zhang, Xingran Chen, Hanzhi Yin, Yiqi Liu, Jiawen Huang, Zeyue Tian, Binyue Deng, et al. Marble: Music audio representation benchmark for universal evaluation. Advances in Neural Information Processing Systems, 36:39626–39647, 2023. find
  66. Xiang Yue, Yuansheng Ni, Kai Zhang, Tianyu Zheng, Ruoqi Liu, Ge Zhang, Samuel Stevens, Dongfu Jiang, Weiming Ren, Yuxuan Sun, et al. Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi. arXiv:2311.16502, 2023. find our card
  67. Xiang Yue, Tianyu Zheng, Yuansheng Ni, Yubo Wang, Kai Zhang, Shengbang Tong, Yuxuan Sun, Ming Yin, Botao Yu, Ge Zhang, et al. Mmmu-pro: A more robust multi-discipline multimodal understanding benchmark. arXiv preprint arXiv:2409.02813, 2024. find
  68. Yongyi Zang, Sean O’Brien, Taylor Berg-Kirkpatrick, Julian McAuley, and Zachary Novack. Are you really listening? boosting perceptual awareness in music-qa benchmarks. arXiv preprint arXiv:2504.00369, 2025. — [arXiv:2504.00369](https://arxiv.org/abs/2504.00369) find
  69. Bowen Zhang, Congchao Guo, Geng Yang, Hang Yu, Haozhe Zhang, Heidi Lei, Jialong Mai, Junjie Yan, Kaiyue Yang, Mingqi Yang, Peikai Huang, Ruiyang Jin, Sitan Jiang, Weihua Cheng, Yawei Li, Yichen Xiao, Yiying Zhou, Yongmao Zhang, Yuan Lu, and Yucen He. Minimax-speech: Intrinsic zero-shot text-to-speec… — [arXiv:2505.07916](https://arxiv.org/abs/2505.07916) find
  70. Chujie Zheng, Shixuan Liu, Mingze Li, Xiong-Hui Chen, Bowen Yu, Chang Gao, Kai Dang, Yuqiong Liu, Rui Men, An Yang, et al. Group sequence policy optimization. arXiv preprint arXiv:2507.18071, 2025. find our card
  71. Jeffrey Zhou, Tianjian Lu, Swaroop Mishra, Siddhartha Brahma, Sujoy Basu, Yi Luan, Denny Zhou, and Le Hou. Instruction-following evaluation for large language models. CoRR, abs/2311.07911, 2023. find our card
  72. Junjie Zhou, Yan Shu, Bo Zhao, Boya Wu, Zhengyang Liang, Shitao Xiao, Minghao Qin, Xi Yang, Yongping Xiong, Bo Zhang, Tiejun Huang, and Zheng Liu. MLVU: benchmarking multi-task long video understanding. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2025, Nashville, TN, USA,… find
  73. Ziwei Zhou, Rui Wang, and Zuxuan Wu. Daily-omni: Towards audio-visual reasoning with temporal alignment across modalities. CoRR, abs/2505.17862, 2025b. — [arXiv:2505.17862](https://arxiv.org/abs/2505.17862) find
  74. Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv:2304.10592, 2023. find our card
  75. Haina Zhu, Yizhi Zhou, Hangting Chen, Jianwei Yu, Ziyang Ma, Rongzhi Gu, Yi Luo, Wei Tan, and Xie Chen. Muq: Self-supervised music representation learning with mel residual vector quantization. arXiv preprint arXiv:2501.01108, 2025. — [arXiv:2501.01108](https://arxiv.org/abs/2501.01108) find