Elamur Research⌕
☰
home / papers / 2026 / UniCM: A Unified Consistency Model For Efficient Multimodal Generation and Understanding

UniCM: A Unified Consistency Model For Efficient Multimodal Generation and Understanding

Paper · 2026 · Chenkai Xu, Xu Wang, Zhenyi Liao et al.

Summary

Unified multimodal models, which handle both text-to-image generation and image understanding in one backbone, are slow because both directions require many iterative decoding steps. The authors propose UniCM, which extends consistency distillation to such models. The obstacle is that consistency training requires a denoising-style trajectory for both modalities. They solve this by representing images and text as discrete tokens and giving each modality its own trajectory:

  • Images: standard masked (discrete) diffusion.
  • Text: the parallel (Jacobi-style) decoding trace of an autoregressive model, following CLLMs, rather than diffusion language models, which the authors consider weaker.

UniCM is initialized from Show-o and fine-tuned on trajectories collected from it, using COCO 2017 prompts for text-to-image and LLaVA instruction data for image-to-text. A single objective trains the model to map any trajectory point to the same endpoint. Trajectory segmentation and regularization keep training stable.

The resulting model produces competitive 512×512 images in 2–4 steps without classifier-free guidance and speeds up text generation. This shows that few-step inference can be achieved for generation and understanding inside one shared model.

Key points

  • Training and evaluation setup: training took 36 hours on 8 A100-40GB GPUs. Latency was measured on one RTX 4090 GPU with batch size 1.
  • Text-to-image results: UniCM beats SD3 on GenEval, Image Reward and CLIP Score at roughly 1/8 of SD3's sampling time. In 2–8 step sampling it also outperforms SDXL-Turbo, Hyper-SD3, Emu3-Gen and Chameleon on GenEval.
  • Image-to-text results: UniCM exceeds Show-o on MMMU and ScienceQA-IMG and is about 1.5× faster on NoCaps. With a well-chosen parallel-decoding block size, the speedup reaches up to 2.3× on long outputs.
  • Caption quality trade-off: captioning scores on NoCaps and Flickr30K drop slightly. The authors attribute this to error accumulation in few-step sampling and to the small distillation set (about 120k COCO prompts).
  • Ablations:
    • Four trajectory segments work better than one or two.
    • Removing the regularization terms (β=0, γ=0) makes training collapse.
    • Top-k sampling noticeably improves 2- and 4-step image generation.

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

🎓Shanghai Jiao Tong UniversityShanghai · China212 works · 19,544 citations🏢Huawei TechnologiesShenzhen · China96 works · 15,432 citations🎓Tongji UniversityShanghai · China33 works · 2,993 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 worksComputer Vision and Pattern Recognition · 3,486 works

🧭 Topics 1Research subjects and languages the work is about.Vision & language · 811 works

Cite

Cite as Chenkai Xu, Xu Wang, Zhenyi Liao, Yishun Li, TianQi Hou and Zhijie Deng. 2026. UniCM: A Unified Consistency Model For Efficient Multimodal Generation and 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.906

@inproceedings{xu2026unicm,
  title = {{UniCM: A Unified Consistency Model For Efficient Multimodal Generation and Understanding}},
  author = {Chenkai Xu, Xu Wang, Zhenyi Liao, Yishun Li, TianQi Hou and Zhijie Deng},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.906},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.906}
}

References

75 references, 32 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Harsh Agrawal, Karan Desai, Yufei Wang, Xinlei Chen, Rishabh Jain, Mark Johnson, Dhruv Batra, Devi Parikh, Stefan Lee, and Peter Anderson. 2019. Nocaps: Novel object captioning at scale. In Proceedings of the IEEE/CVF international conference on computer vision, pages 8948–8957. find
  2. Jinbin Bai, Tian Ye, Wei Chow, Enxin Song, Qing-Guo Chen, Xiangtai Li, Zhen Dong, Lei Zhu, and Shuicheng Yan. 2024. Meissonic: Revitalizing masked generative transformers for efficient high-resolution text-to-image synthesis. In The Thirteenth International Conference on Learning Representations. find
  3. Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023. Qwen-vl: A frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966.
  4. Satanjeev Banerjee and Alon Lavie. 2005. Meteor: An automatic metric for mt evaluation with improved correlation with human judgments. In Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and/or summarization, pages 65–72.
  5. Huiwen Chang, Han Zhang, Jarred Barber, AJ Maschinot, Jose Lezama, Lu Jiang, Ming-Hsuan Yang, Kevin Murphy, William T Freeman, Michael Rubinstein, and 1 others. 2023. Muse: Text-to-image generation via masked generative transformers. arXiv preprint arXiv:2301.00704. — [arXiv:2301.00704](https://arxiv.org/abs/2301.00704) find
  6. Huiwen Chang, Han Zhang, Lu Jiang, Ce Liu, and William T Freeman. 2022. Maskgit: Masked generative image transformer. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11315–11325. find
  7. Junsong Chen, Yue Wu, Simian Luo, Enze Xie, Sayak Paul, Ping Luo, Hang Zhao, and Zhenguo Li. 2024. Pixart-δ: Fast and controllable image generation with latent consistency models. arXiv preprint arXiv:2401.05252. find
  8. Junsong Chen, Jincheng Yu, Chongjian Ge, Lewei Yao, Enze Xie, Yue Wu, Zhongdao Wang, James Kwok, Ping Luo, Huchuan Lu, and 1 others. 2023. Pixart-α: Fast training of diffusion transformer for photorealistic text-to-image synthesis. arXiv preprint arXiv:2310.00426.
  9. Runpei Dong, Chunrui Han, Yuang Peng, Zekun Qi, Zheng Ge, Jinrong Yang, Liang Zhao, Jianjian Sun, Hongyu Zhou, Haoran Wei, and 1 others. 2023. Dreamllm: Synergistic multimodal comprehension and creation. arXiv preprint arXiv:2309.11499. — [arXiv:2309.11499](https://arxiv.org/abs/2309.11499) find
  10. Patrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari, Jonas Müller, Harry Saini, Yam Levi, Dominik Lorenz, Axel Sauer, Frederic Boesel, and 1 others. 2024. Scaling rectified flow transformers for high-resolution image synthesis. In Forty-first International Conference on Machine Learning. find
  11. Kaituo Feng, Kaixiong Gong, Bohao Li, Zonghao Guo, Yibing Wang, Tianshuo Peng, Benyou Wang, and Xiangyu Yue. 2025. Video-r1: Reinforcing video reasoning in mllms. arXiv preprint arXiv:2503.21776. — [arXiv:2503.21776](https://arxiv.org/abs/2503.21776) find
  12. Dhruba Ghosh, Hanna Hajishirzi, and Ludwig Schmidt. 2023. Geneval: An object-focused framework for evaluating text-to-image alignment. Preprint, arXiv:2310.11513. — [arXiv:2310.11513](https://arxiv.org/abs/2310.11513) find
  13. Shansan Gong, Shivam Agarwal, Yizhe Zhang, Jiacheng Ye, Lin Zheng, Mukai Li, Chenxin An, Peilin Zhao, Wei Bi, Jiawei Han, and 1 others. 2024. Scaling diffusion language models via adaptation from autoregressive models. arXiv preprint arXiv:2410.17891. — [arXiv:2410.17891](https://arxiv.org/abs/2410.17891) find
  14. Satoshi Hayakawa, Yuhta Takida, Masaaki Imaizumi, Hiromi Wakaki, and Yuki Mitsufuji. 2024. Distillation of discrete diffusion through dimensional correlations. arXiv preprint arXiv:2410.08709. — [arXiv:2410.08709](https://arxiv.org/abs/2410.08709) find
  15. Jonathan Heek, Emiel Hoogeboom, and Tim Salimans. 2024. Multistep consistency models. arXiv preprint arXiv:2403.06807. — [arXiv:2403.06807](https://arxiv.org/abs/2403.06807) find
  16. Jack Hessel, Ari Holtzman, Maxwell Forbes, Ronan Le Bras, and Yejin Choi. 2022. Clipscore: A reference-free evaluation metric for image captioning. Preprint, arXiv:2104.08718.
  17. Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, 33:6840– 6851. find
  18. Jonathan Ho and Tim Salimans. 2021. Classifier-free diffusion guidance. In NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications.
  19. Ethan Chern, Jiadi Su, Yan Ma, and Pengfei Liu. 2024. Anole: An open, autoregressive, native large multimodal models for interleaved image-text generation. arXiv preprint arXiv:2407.06135. — [arXiv:2407.06135](https://arxiv.org/abs/2407.06135) find
  20. Drew A Hudson and Christopher D Manning. 2019. Gqa: A new dataset for real-world visual reasoning and compositional question answering. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 6700–6709.
  21. Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi. 2023. Instructblip: Towards general-purpose vision-language models with instruction tuning. Preprint, arXiv:2305.06500.
  22. Dongjun Kim, Chieh-Hsin Lai, Wei-Hsiang Liao, Naoki Murata, Yuhta Takida, Toshimitsu Uesaka, Yutong He, Yuki Mitsufuji, and Stefano Ermon. 2023. Consistency trajectory models: Learning probability flow ode trajectory of diffusion. arXiv preprint arXiv:2310.02279. find
  23. Siqi Kou, Lanxiang Hu, Zhezhi He, Zhijie Deng, and Hao Zhang. 2024a. Cllms: Consistency large language models. arXiv preprint arXiv:2403.00835. — [arXiv:2403.00835](https://arxiv.org/abs/2403.00835) find
  24. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024d. Visual instruction tuning. Advances in neural information processing systems, 36.
  25. Siqi Kou, Jiachun Jin, Zhihong Liu, Chang Liu, Ye Ma, Jian Jia, Quan Chen, Peng Jiang, and Zhijie Deng. 2024b. Orthus: Autoregressive interleaved image-text generation with modality-specific heads. arXiv preprint arXiv:2412.00127. find
  26. Pan Lu, Swaroop Mishra, Tanglin Xia, Liang Qiu, Kai-Wei Chang, Song-Chun Zhu, Oyvind Tafjord, Peter Clark, and Ashwin Kalyan. 2022. Learn to explain: Multimodal reasoning via thought chains for science question answering. Advances in Neural Information Processing Systems, 35:2507–2521. find
  27. Bo Li, Yuanhan Zhang, Dong Guo, Renrui Zhang, Feng Li, Hao Zhang, Kaichen Zhang, Yanwei Li, Ziwei Liu, and Chunyuan Li. 2024a. Llava-onevision: Easy visual task transfer. arXiv preprint arXiv:2408.03326.
  28. Yifan Li, Yifan Du, Kun Zhou, Jinpeng Wang, Wayne Xin Zhao, and Ji-Rong Wen. 2023. Evaluating object hallucination in large vision-language models. arXiv preprint arXiv:2305.10355.
  29. Yuhui Li, Fangyun Wei, Chao Zhang, and Hongyang Zhang. 2024b. Eagle-2: Faster inference of language models with dynamic draft trees. arXiv preprint arXiv:2406.16858.
  30. Zhimin Li, Jianwei Zhang, Qin Lin, Jiangfeng Xiong, Yanxin Long, Xinchi Deng, Yingfang Zhang, Xingchao Liu, Minbin Huang, Zedong Xiao, and 1 others. 2024c. Hunyuan-dit: A powerful multi-resolution diffusion transformer with fine-grained chinese understanding. arXiv preprint arXiv:2405.08748.
  31. Bin Lin, Zhenyu Tang, Yang Ye, Jiaxi Cui, Bin Zhu, Peng Jin, Jinfa Huang, Junwu Zhang, Yatian Pang, Munan Ning, and 1 others. 2024. Moe-llava: Mixture of experts for large vision-language models. arXiv preprint arXiv:2401.15947. — [arXiv:2401.15947](https://arxiv.org/abs/2401.15947) find
  32. Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer Vision– ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pag…
  33. Hao Liu, Wilson Yan, Matei Zaharia, and Pieter Abbeel. 2024a. World model on million-length video and language with blockwise ringattention. arXiv preprint arXiv:2402.08268.
  34. Haotian Liu, Chunyuan Li, Yuheng Li, and Yong Jae Lee. 2024b. Improved baselines with visual instruction tuning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 26296–26306.
  35. Haotian Liu, Chunyuan Li, Yuheng Li, Bo Li, Yuanhan Zhang, Sheng Shen, and Yong Jae Lee. 2024c. Llava-next: Improved reasoning, ocr, and world knowledge. find
  36. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. Advances in neural information processing systems, 36:34892– 34916.
  37. Simian Luo, Yiqin Tan, Longbo Huang, Jian Li, and Hang Zhao. 2023. Latent consistency models: Synthesizing high-resolution images with few-step inference. arXiv preprint arXiv:2310.04378.
  38. Xiaoxiao Ma, Mohan Zhou, Tao Liang, Yalong Bai, Tiejun Zhao, Huaian Chen, and Yi Jin. 2024. Star: Scale-wise text-to-image generation via auto-regressive representations. arXiv preprint arXiv:2406.10797. find
  39. Shen Nie, Fengqi Zhu, Chao Du, Tianyu Pang, Qian Liu, Guangtao Zeng, Min Lin, and Chongxuan Li. 2024. Scaling up masked diffusion models on text. arXiv preprint arXiv:2410.18514. — [arXiv:2410.18514](https://arxiv.org/abs/2410.18514) find
  40. 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. arXiv preprint arXiv:2502.09992.
  41. Guilherme Penedo, Quentin Malartic, Daniel Hesslow, Ruxandra Cojocaru, Alessandro Cappelli, Hamza Alobeidli, Baptiste Pannier, Ebtesam Almazrouei, and Julien Launay. 2023. The refinedweb dataset for falcon llm: outperforming curated corpora with web data, and web data only. arXiv preprint arXiv:2306… find
  42. Bryan A. Plummer, Liwei Wang, Christopher M. Cervantes, Juan C. Caicedo, Julia Hockenmaier, and Svetlana Lazebnik. 2017. Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models. IJCV, 123(1):74–93. find
  43. Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas Müller, Joe Penna, and Robin Rombach. Sdxl: Improving latent diffusion models for high-resolution image synthesis. In The Twelfth International Conference on Learning Representations.
  44. Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas Müller, Joe Penna, and Robin Rombach. 2023. Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952.
  45. Yuxi Ren, Xin Xia, Yanzuo Lu, Jiacheng Zhang, Jie Wu, Pan Xie, Xing Wang, and Xuefeng Xiao. 2024. Hyper-sd: Trajectory segmented consistency model for efficient image synthesis. arXiv preprint arXiv:2404.13686. — [arXiv:2404.13686](https://arxiv.org/abs/2404.13686) find
  46. Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Björn Ommer. 2022. High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10684–10695.
  47. Axel Sauer, Dominik Lorenz, Andreas Blattmann, and Robin Rombach. 2024. Adversarial diffusion distillation. In European Conference on Computer Vision, pages 87–103. Springer. find
  48. Haozhan Shen, Peng Liu, Jingcheng Li, Chunxin Fang, Yibo Ma, Jiajia Liao, Qiaoli Shen, Zilun Zhang, Kangjia Zhao, Qianqian Zhang, and 1 others. 2025. Vlm-r1: A stable and generalizable r1-style large vision-language model. arXiv preprint arXiv:2504.07615.
  49. Yang Song and Prafulla Dhariwal. 2023. Improved techniques for training consistency models. arXiv preprint arXiv:2310.14189. find
  50. Yang Song, Prafulla Dhariwal, Mark Chen, and Ilya Sutskever. 2023. Consistency models. arXiv preprint arXiv:2303.01469. find
  51. Yang Song, Jascha Sohl-Dickstein, Diederik P Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole. 2020. Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456.
  52. Peize Sun, Yi Jiang, Shoufa Chen, Shilong Zhang, Bingyue Peng, Ping Luo, and Zehuan Yuan. 2024. Autoregressive model beats diffusion: Llama for scalable image generation. arXiv preprint arXiv:2406.06525. — [arXiv:2406.06525](https://arxiv.org/abs/2406.06525) find
  53. Chameleon Team. 2024a. Chameleon: Mixed-modal early-fusion foundation models. arXiv preprint arXiv:2405.09818.
  54. Chameleon Team. 2024b. Chameleon: Mixed-modal early-fusion foundation models, 2024. URL https://arxiv.org/abs/2405.09818, 9. ↗
  55. Gemini Team, Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M Dai, Anja Hauth, Katie Millican, and 1 others. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805.
  56. Aaron Van Den Oord, Oriol Vinyals, and 1 others. 2017. Neural discrete representation learning. Advances in neural information processing systems, 30. find
  57. Fu-Yun Wang, Zhaoyang Huang, Alexander William Bergman, Dazhong Shen, Peng Gao, Michael Lingelbach, Keqiang Sun, Weikang Bian, Guanglu Song, Yu Liu, and 1 others. 2024a. Phased consistency model. arXiv preprint arXiv:2405.18407. — [arXiv:2405.18407](https://arxiv.org/abs/2405.18407) find
  58. Xinlong Wang, Xiaosong Zhang, Zhengxiong Luo, Quan Sun, Yufeng Cui, Jinsheng Wang, Fan Zhang, Yueze Wang, Zhen Li, Qiying Yu, and 1 others. 2024b. Emu3: Next-token prediction is all you need. arXiv preprint arXiv:2409.18869. — [arXiv:2409.18869](https://arxiv.org/abs/2409.18869) find
  59. Chengyue Wu, Xiaokang Chen, Zhiyu Wu, Yiyang Ma, Xingchao Liu, Zizheng Pan, Wen Liu, Zhenda Xie, Xingkai Yu, Chong Ruan, and 1 others. 2024. Janus: Decoupling visual encoding for unified multimodal understanding and generation. arXiv preprint arXiv:2410.13848.
  60. Shengqiong Wu, Hao Fei, Leigang Qu, Wei Ji, and Tat-Seng Chua. 2023a. Next-gpt: Any-to-any multimodal llm. arXiv preprint arXiv:2309.05519.
  61. Xiaoshi Wu, Yiming Hao, Keqiang Sun, Yixiong Chen, Feng Zhu, Rui Zhao, and Hongsheng Li. 2023b. Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis. arXiv preprint arXiv:2306.09341. — [arXiv:2306.09341](https://arxiv.org/abs/2306.09341) find
  62. Jinheng Xie, Weijia Mao, Zechen Bai, David Junhao Zhang, Weihao Wang, Kevin Qinghong Lin, Yuchao Gu, Zhijie Chen, Zhenheng Yang, and Mike Zheng Shou. 2024a. Show-o: One single transformer to unify multimodal understanding and generation. arXiv preprint arXiv:2408.12528. — [arXiv:2408.12528](https://arxiv.org/abs/2408.12528) find
  63. Qingsong Xie, Zhenyi Liao, Zhijie Deng, Shixiang Tang, Haonan Lu, and 1 others. 2024b. Mlcm: Multi-step consistency distillation of latent diffusion model. arXiv preprint arXiv:2406.05768. find
  64. Jiazheng Xu, Xiao Liu, Yuchen Wu, Yuxuan Tong, Qinkai Li, Ming Ding, Jie Tang, and Yuxiao Dong. 2023. Imagereward: Learning and evaluating human preferences for text-to-image generation. Preprint, arXiv:2304.05977. find
  65. Zhuoyi Yang, Jiayan Teng, Wendi Zheng, Ming Ding, Shiyu Huang, Jiazheng Xu, Yuanming Yang, Wenyi Hong, Xiaohan Zhang, Guanyu Feng, and 1 others. 2024. Cogvideox: Text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:2408.06072.
  66. Jiacheng Ye, Zhihui Xie, Lin Zheng, Jiahui Gao, Zirui Wu, Xin Jiang, Zhenguo Li, and Lingpeng Kong. 2025. Dream 7b. find
  67. Qinghao Ye, Haiyang Xu, Jiabo Ye, Ming Yan, Anwen Hu, Haowei Liu, Qi Qian, Ji Zhang, and Fei Huang. 2024. mplug-owl2: Revolutionizing multimodal large language model with modality collaboration. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13040–13051. find
  68. Peter Young, Alice Lai, Micah Hodosh, and Julia Hockenmaier. 2014. From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions. TACL, 2:67–78. find
  69. Lijun Yu, Yong Cheng, Kihyuk Sohn, José Lezama, Han Zhang, Huiwen Chang, Alexander G Hauptmann, Ming-Hsuan Yang, Yuan Hao, Irfan Essa, and 1 others. 2023. Magvit: Masked generative video transformer. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10459–10… find
  70. Xiang Yue, Yuansheng Ni, Kai Zhang, Tianyu Zheng, Ruoqi Liu, Ge Zhang, Samuel Stevens, Dongfu Jiang, Weiming Ren, Yuxuan Sun, and 1 others. 2024. Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi. In Proceedings of the IEEE/CVF Conference on Computer Vi…
  71. Chuyang Zhao, Yuxing Song, Wenhao Wang, Haocheng Feng, Errui Ding, Yifan Sun, Xinyan Xiao, and Jingdong Wang. 2024. Monoformer: One transformer for both diffusion and autoregression. arXiv preprint arXiv:2409.16280. — [arXiv:2409.16280](https://arxiv.org/abs/2409.16280) find
  72. Jianbin Zheng, Minghui Hu, Zhongyi Fan, Chaoyue Wang, Changxing Ding, Dacheng Tao, and Tat-Jen Cham. 2024. Trajectory consistency distillation. arXiv preprint arXiv:2402.19159. — [arXiv:2402.19159](https://arxiv.org/abs/2402.19159) find
  73. Chunting Zhou, Lili Yu, Arun Babu, Kushal Tirumala, Michihiro Yasunaga, Leonid Shamis, Jacob Kahn, Xuezhe Ma, Luke Zettlemoyer, and Omer Levy. 2024. Transfusion: Predict the next token and diffuse images with one multi-modal model. arXiv preprint arXiv:2408.11039.
  74. Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2023. Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592.
  75. Yichen Zhu, Minjie Zhu, Ning Liu, Zhicai Ou, Xiaofeng Mou, and Jian Tang. 2024. Llava-phi: Efficient multimodal assistant with small language model. arXiv preprint arXiv:2401.02330. — [arXiv:2401.02330](https://arxiv.org/abs/2401.02330) find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/xu-2026-unicm-unified-consistency-model-efficient/