Elamur Research⌕
☰
home / papers / 2026 / UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision

UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision

Paper · 2026 · Zhen Fang, Ruiyan Han, XinYu Sun et al.

Summary

Unified Multimodal Models (UMMs) often judge images accurately but cannot produce scenes of the same quality themselves. The authors call this mismatch "Conduction Aphasia." They propose UniCorn, a post-training method in which one model teaches itself, with no outside data or teacher model. The same UMM takes three roles in turn:

  • a Proposer writes varied prompts,
  • a Solver generates candidate images,
  • a Judge scores the results.

A step called Cognitive Pattern Reconstruction then turns these raw exchanges into three kinds of training data: captions, judgements and reflections. These are combined with the best self-generated text-to-image samples for fine-tuning.

To check that understanding and generation stay consistent, the authors also release UniCycle. This benchmark has the model draw an image from a text and then describe that image, and it measures how much of the original meaning survives.

Applied mainly to BAGEL, UniCorn improves image generation across six benchmarks without harming comprehension. This suggests self-supervision alone can scale unified models.

Key points

  • State-of-the-art scores: TIIF 73.8, DPG 86.8, CompBench 88.5 and UniCycle (Hard) 46.5. The method also improves GenEval by +4.0, WISE by +5.0 and OneIG by +6.5.
  • UniCycle comparison: UniCorn beats its base BAGEL by nearly 10 points. A variant trained on data from Qwen3-VL-235B-A22B-Instruct (UniCorn*) trails by 6.5 points, which suggests a stronger external teacher brings little benefit.
  • Data efficiency: With only 5k self-generated samples, UniCorn surpasses IRG, which was trained on 30k GPT-4o-distilled examples, and DALL·E 3 on TIIF.
  • Transfer to another model: Applied to Janus Pro, the method improves TIIF by +2.7, WISE by +7.0 and OneIG-EN by +4.7.
  • Limitations: The self-play is single-turn and adds compute cost. Understanding metrics show no notable gains.

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, 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 Zhen Fang, Ruiyan Han, XinYu Sun, Yuchen Ma, Ziheng Wang, Yu Zeng, Zehui Chen, Lin Chen, Wenxuan Huang, Wei-Jie Xu, Yi Cao and Feng Zhao. 2026. UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-long.621

@inproceedings{fang2026unicorn,
  title = {{UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision}},
  author = {Zhen Fang, Ruiyan Han, XinYu Sun, Yuchen Ma, Ziheng Wang, Yu Zeng, Zehui Chen, Lin Chen, Wenxuan Huang, Wei-Jie Xu, Yi Cao and Feng Zhao},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.621},
  url = {https://doi.org/10.18653/v1/2026.acl-long.621}
}

References

148 references, 48 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, and 1 others. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774.
  2. Ruichuan An, Sihan Yang, Ziyu Guo, Wei Dai, Zijun Shen, Haodong Li, Renrui Zhang, Xinyu Wei, Guopeng Li, Wenshan Wu, and 1 others. 2026. Genius: Generative fluid intelligence evaluation suite. arXiv preprint arXiv:2602.11144. text-to-image system for enhanced prompt interpretation and interactive ge… — [arXiv:2602.11144](https://arxiv.org/abs/2602.11144) find
  3. Jiuhai Chen, Zhiyang Xu, Xichen Pan, Yushi Hu, Can Qin, Tom Goldstein, Lifu Huang, Tianyi Zhou, Saining Xie, Silvio Savarese, and 1 others. 2025b. Blip3-o: A family of fully open unified multimodal models-architecture, training and dataset. arXiv preprint arXiv:2505.09568. find
  4. Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, and 1 others. 2025. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923. — Qwen2.5-VL Technical Report
  5. Jiuhai Chen, Zhiyang Xu, Xichen Pan, Yushi Hu, Can Qin, Tom Goldstein, Lifu Huang, Tianyi Zhou, Saining Xie, Silvio Savarese, and 1 others. 2025c. Blip3-o: A family of fully open unified multimodal models-architecture, training and dataset. arXiv preprint arXiv:2505.09568. find
  6. James Betker, Gabriel Goh, Li Jing, Tim Brooks, Jianfeng Wang, Linjie Li, Long Ouyang, Juntang Zhuang, Joyce Lee, Yufei Guo, and 1 others. 2023a. Improving image generation with better captions. Computer Science. https://cdn.openai. com/papers/dalle-3. pdf, 2(3):8. ↗
  7. Junsong Chen, Chongjian Ge, Enze Xie, Yue Wu, Lewei Yao, Xiaozhe Ren, Zhongdao Wang, Ping Luo, Huchuan Lu, and Zhenguo Li. 2024b. Pixart-sigma: Weak-to-strong training of diffusion transformer for 4k text-to-image generation. In European Conference on Computer Vision. find
  8. James Betker, Gabriel Goh, Li Jing, Tim Brooks, Jianfeng Wang, Linjie Li, Long Ouyang, Juntang Zhuang, Joyce Lee, Yufei Guo, and 1 others. 2023b. Improving image generation with better captions. OpenAI blog. find
  9. Lin Chen, Jinsong Li, Xiaoyi Dong, Pan Zhang, Yuhang Zang, Zehui Chen, Haodong Duan, Jiaqi Wang, Yu Qiao, Dahua Lin, and 1 others. 2024c. Are we on the right way for evaluating large vision-language models? Advances in Neural Information Processing Systems, 37:27056–27087.
  10. Ignacio Matte Blanco. 2018. The unconscious as infinite sets: An essay in bi-logic. Routledge. find
  11. Minwoo Byeon, Beomhee Park, Haecheon Kim, Sungjun Lee, Woonhyuk Baek, and Saehoon Kim. 2022. Coyo-700m: Image-text pair dataset. find
  12. Huanqia Cai, Sihan Cao, Ruoyi Du, Peng Gao, Steven Hoi, Shijie Huang, Zhaohui Hou, Dengyang Jiang, Xin Jin, Liangchen Li, and 1 others. 2025. Z-image: An efficient image generation foundation model with single-stream diffusion transformer. arXiv preprint arXiv:2511.22699. find
  13. Mert Cemri, Melissa Z Pan, Shuyi Yang, Lakshya A Agrawal, Bhavya Chopra, Rishabh Tiwari, Kurt Keutzer, Aditya Parameswaran, Dan Klein, Kannan Ramchandran, and 1 others. 2025. Why do multi-agent llm systems fail? arXiv preprint arXiv:2503.13657.
  14. Jingjing Chang, Yixiao Fang, Peng Xing, Shuhan Wu, Wei Cheng, Rui Wang, Xianfang Zeng, Gang Yu, and Hai-Bao Chen. 2025. Oneig-bench: Omni-dimensional nuanced evaluation for image generation. Preprint, arXiv:2506.07977. — [arXiv:2506.07977](https://arxiv.org/abs/2506.07977) find
  15. Boyuan Chen, Diego Martí Monsó, Yilun Du, Max Simchowitz, Russ Tedrake, and Vincent Sitzmann. 2024a. Diffusion forcing: Next-token prediction meets full-sequence diffusion. In NeurIPS. find
  16. Chieh-Yun Chen, Min Shi, Gong Zhang, and Humphrey Shi. 2025a. T2i-copilot: A training-free multi-agent Weize Chen, Yusheng Su, Jingwei Zuo, Cheng Yang, Chenfei Yuan, Chi-Min Chan, Heyang Yu, Yaxi Lu, Yi-Hsin Hung, Chen Qian, and 1 others. 2024d. Agentverse: Facilitating multi-agent collaboration and…
  17. Xiaokang Chen, Chengyue Wu, Zhiyu Wu, Yiyang Ma, Xingchao Liu, Zizheng Pan, Wen Liu, Zhenda Xie, Xingkai Yu, Chong Ruan, and Ping Luo. 2025d. Janus-pro: Unified multimodal understanding and generation with data and model scaling. arXiv preprint arXiv:2501.17811.
  18. Xiaokang Chen, Zhiyu Wu, Xingchao Liu, Zizheng Pan, Wen Liu, Zhenda Xie, Xingkai Yu, and Chong Ruan. 2025e. Janus-pro: Unified multimodal understanding and generation with data and model scaling. arXiv preprint arXiv:2501.17811.
  19. Yixing Chen, Yiding Wang, Siqi Zhu, Haofei Yu, Tao Feng, Muhan Zhang, Mostofa Patwary, and Jiaxuan You. 2025f. Multi-agent evolve: Llm self-improve through co-evolution. arXiv preprint arXiv:2510.23595. — [arXiv:2510.23595](https://arxiv.org/abs/2510.23595) find
  20. Zehui Chen, Kuikun Liu, Qiuchen Wang, Wenwei Zhang, Jiangning Liu, Dahua Lin, Kai Chen, and Feng Zhao. 2024e. Agent-flan: Designing data and methods of effective agent tuning for large language models. Annual Meeting of the Association for Computational Linguistics.
  21. Zihao Cheng, Zeming Liu, Yingyu Shan, Xinyi Wang, Xiangrong Zhu, Yunpu Ma, Hongru Wang, Yuhang Guo, Wei Lin, and Yunhong Wang. 2026. Mem 2 evolve: Towards self-evolving agents via co-evolutionary capability expansion and experience distillation. Preprint, arXiv:2604.10923.
  22. Eugene Choi, Arash Ahmadian, Matthieu Geist, Oil-vier Pietquin, and Mohammad Gheshlaghi Azar. 2024. Self-improving robust preference optimization. arXiv preprint arXiv:2406.01660. — [arXiv:2406.01660](https://arxiv.org/abs/2406.01660) find
  23. Yufeng Cui, Honghao Chen, Haoge Deng, Xu Huang, Xinghang Li, Jirong Liu, Yang Liu, Zhuoyan Luo, Jinsheng Wang, Wenxuan Wang, and 1 others. 2025. Emu3. 5: Native multimodal models are world learners. arXiv preprint arXiv:2510.26583. — [arXiv:2510.26583](https://arxiv.org/abs/2510.26583) find
  24. Chaorui Deng, Deyao Zhu, Kunchang Li, Chenhui Gou, Feng Li, Zeyu Wang, Shu Zhong, Weihao Yu, Xiaonan Nie, Ziang Song, Guang Shi, and Haoqi Fan. 2025a. Emerging properties in unified multimodal pretraining. arXiv preprint arXiv:2505.14683. — [arXiv:2505.14683](https://arxiv.org/abs/2505.14683) find
  25. Chaorui Deng, Deyao Zhu, Kunchang Li, Chenhui Gou, Feng Li, Zeyu Wang, Shu Zhong, Weihao Yu, Xiaonan Nie, Ziang Song, and 1 others. 2025b. Emerging properties in unified multimodal pretraining. arXiv preprint arXiv:2505.14683. — [arXiv:2505.14683](https://arxiv.org/abs/2505.14683) find
  26. Qingxiu Dong, Lei Li, Damai Dai, Ce Zheng, Jingyuan Ma, Rui Li, Heming Xia, Jingjing Xu, Zhiyong Wu, Baobao Chang, and 1 others. 2024. A survey on in-context learning. In Proceedings of the 2024 conference on empirical methods in natural language processing, pages 1107–1128.
  27. John Dunlosky and Janet Metcalfe. 2008. Metacognition. Sage Publications. find
  28. 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 ICML. find
  29. Zhen Fang, Zhuoyang Liu, Jiaming Liu, Hao Chen, Yu Zeng, Shiting Huang, Zehui Chen, Lin Chen, Shanghang Zhang, and Feng Zhao. 2025. Dualvla: Building a generalizable embodied agent via partial decoupling of reasoning and action. arXiv preprint arXiv:2511.22134. — [arXiv:2511.22134](https://arxiv.org/abs/2511.22134) find
  30. Yuanning Feng, Sinan Wang, Zhengxiang Cheng, Yao Wan, and Dongping Chen. 2025. Are we on the right way to assessing llm-as-a-judge? arXiv preprint arXiv:2512.16041. — [arXiv:2512.16041](https://arxiv.org/abs/2512.16041) find
  31. Chaoyou Fu, Peixian Chen, Yunhang Shen, Yulei Qin, Mengdan Zhang, Xu Lin, Jinrui Yang, Xiawu Zheng, Ke Li, Xing Sun, and 1 others. 2023. Mme: A comprehensive evaluation benchmark for multimodal large language models. arXiv preprint arXiv:2306.13394.
  32. Yuying Ge, Sijie Zhao, Jinguo Zhu, Yixiao Ge, Kun Yi, Lin Song, Chen Li, Xiaohan Ding, and Ying Shan. 2024. Seed-x: Multimodal models with unified multi-granularity comprehension and generation. arXiv preprint arXiv:2404.14396. — [arXiv:2404.14396](https://arxiv.org/abs/2404.14396) find
  33. Dhruba Ghosh, Hannaneh Hajishirzi, and Ludwig Schmidt. 2023. Geneval: An object-focused framework for evaluating text-to-image alignment. In NeurIPS. find
  34. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, and 1 others. 2025a. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948.
  35. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, and 1 others. 2025b. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948.
  36. Ziyu Guo, Renrui Zhang, Hongyu Li, Manyuan Zhang, Xinyan Chen, Sifan Wang, Yan Feng, Peng Pei, and Pheng-Ann Heng. 2025c. Thinking-while-generating: Interleaving textual reasoning throughout visual generation. arXiv preprint arXiv:2511.16671. — [arXiv:2511.16671](https://arxiv.org/abs/2511.16671) find
  37. Xiwei Hu, Rui Wang, Yixiao Fang, Bin Fu, Pei Cheng, and Gang Yu. 2024. Ella: Equip diffusion models with llm for enhanced semantic alignment. arXiv preprint arXiv:2403.05135. — [arXiv:2403.05135](https://arxiv.org/abs/2403.05135) find
  38. Yushi Hu, Reyhane Askari-Hemmat, Melissa Hall, Emily Dinan, Luke Zettlemoyer, and Marjan Ghazvininejad. 2025. Multimodal rewardbench 2: Evaluating omni reward models for interleaved text and image. arXiv preprint arXiv:2512.16899. find
  39. Chengsong Huang, Wenhao Yu, Xiaoyang Wang, Hongming Zhang, Zongxia Li, Ruosen Li, Jiaxin Huang, Haitao Mi, and Dong Yu. 2025a. R-zero: Self-evolving reasoning llm from zero data. arXiv preprint arXiv:2508.05004. — [arXiv:2508.05004](https://arxiv.org/abs/2508.05004) find
  40. Shiting Huang, Zhen Fang, Zehui Chen, Siyu Yuan, Junjie Ye, Yu Zeng, Lin Chen, Qi Mao, and Feng Zhao. 2025b. Critictool: Evaluating self-critique capabilities of large language models in tool-calling error scenarios. arXiv preprint arXiv:2506.13977.
  41. Shiting Huang, Zecheng Li, Yu Zeng, Qingnan Ren, Zhen Fang, Qisheng Su, Kou Shi, Lin Chen, Zehui Chen, and Feng Zhao. 2026a. Internalizing meta-experience into memory for guided reinforcement learning in large language models. arXiv preprint arXiv:2602.10224. — [arXiv:2602.10224](https://arxiv.org/abs/2602.10224) find
  42. Wenxuan Huang. 2025. Interleaving reasoning: Next-generation reasoning systems for agi. GitHub repository. Accessed 2025-08-19. find
  43. Wenxuan Huang, Shuang Chen, Zheyong Xie, Shaosheng Cao, Shixiang Tang, Yufan Shen, Qingyu Yin, Wenbo Hu, Xiaoman Wang, Yuntian Tang, and 1 others. 2025c. Interleaving reasoning for better text-to-image generation. arXiv preprint arXiv:2509.06945. — [arXiv:2509.06945](https://arxiv.org/abs/2509.06945) find
  44. Daiqing Li, Aleks Kamko, Ehsan Akhgari, Ali Sabet, Linmiao Xu, and Suhail Doshi. 2024a. Playground v2. 5: Three insights towards enhancing aesthetic quality in text-to-image generation. arXiv preprint arXiv:2402.17245. — [arXiv:2402.17245](https://arxiv.org/abs/2402.17245) find
  45. Wenxuan Huang, Yu Zeng, Qiuchen Wang, Zhen Fang, Shaosheng Cao, Zheng Chu, Qingyu Yin, Shuang Chen, Zhenfei Yin, Lin Chen, and 1 others. 2026b. Vision-deepresearch: Incentivizing deepresearch capability in multimodal large language models. arXiv preprint arXiv:2601.22060. — [arXiv:2601.22060](https://arxiv.org/abs/2601.22060) find
  46. Dawei Li, Bohan Jiang, Liangjie Huang, Alimohammad Beigi, Chengshuai Zhao, Zhen Tan, Amrita Bhattacharjee, Yuxuan Jiang, Canyu Chen, Tianhao Wu, and 1 others. 2025a. From generation to judgment: Opportunities and challenges of llm-as-a-judge. In Proceedings of the 2025 Conference on Empirical Method… find
  47. Aaron Hurst, Adam Lerer, Adam P Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, and 1 others. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276.
  48. Haitao Li, Qian Dong, Junjie Chen, Huixue Su, Yujia Zhou, Qingyao Ai, Ziyi Ye, and Yiqun Liu. 2024b. Llms-as-judges: a comprehensive survey on llm-based evaluation methods. arXiv preprint arXiv:2412.05579.
  49. Dongzhi Jiang, Ziyu Guo, Renrui Zhang, Zhuofan Zong, Hao Li, Le Zhuo, Shilin Yan, Pheng-Ann Heng, and Hongsheng Li. 2025a. T2i-r1: Reinforcing image generation with collaborative semantic-level and token-level cot. arXiv preprint arXiv:2505.00703. — [arXiv:2505.00703](https://arxiv.org/abs/2505.00703) find
  50. Haodong Li, Chunmei Qing, Huanyu Zhang, Dongzhi Jiang, Yihang Zou, Hongbo Peng, Dingming Li, Yuhong Dai, ZePeng Lin, Juanxi Tian, and 1 others. 2026a. Coco: Code as cot for text-to-image preview and rare concept generation. arXiv preprint arXiv:2603.08652. find
  51. Dongzhi Jiang, Renrui Zhang, Haodong Li, Zhuofan Zong, Ziyu Guo, Jun He, Claire Guo, Jun-yan Ye, Rongyao Fang, Weijia Li, and 1 others. 2025b. Draco: Draft as cot for text-to-image preview and rare concept generation. arXiv preprint arXiv:2512.05112. — [arXiv:2512.05112](https://arxiv.org/abs/2512.05112) find
  52. Haodong Li, Jingwei Wu, Quan Sun, Guopeng Li, Juanxi Tian, Huanyu Zhang, Yanlin Lai, Ruichuan An, Hongbo Peng, Yuhong Dai, and 1 others. 2026b. Gebench: Benchmarking image generation models as gui environments. arXiv preprint arXiv:2602.09007. — [arXiv:2602.09007](https://arxiv.org/abs/2602.09007) find
  53. Weiyang Jin, Yuwei Niu, Jiaqi Liao, Chengqi Duan, Aoxue Li, Shenghua Gao, and Xihui Liu. 2025a. Srum: Fine-grained self-rewarding for unified multimodal models. arXiv preprint arXiv:2510.12784. — [arXiv:2510.12784](https://arxiv.org/abs/2510.12784) find
  54. Mengdi Li, Jiaye Lin, Xufeng Zhao, Wenhao Lu, Peilin Zhao, Stefan Wermter, and Di Wang. 2025b. Curriculum-rlaif: Curriculum alignment with reinforcement learning from ai feedback. arXiv preprint arXiv:2505.20075. find
  55. Zhuoran Jin, Hongbang Yuan, Kejian Zhu, Jiachun Li, Pengfei Cao, Yubo Chen, Kang Liu, and Jun Zhao. 2025b. Omni-reward: Towards generalist omni-modal reward modeling with free-form preferences. arXiv preprint arXiv:2510.23451. — [arXiv:2510.23451](https://arxiv.org/abs/2510.23451) find
  56. Songze Li, Xiaoke Guo, Tianqi Liu, Biao Yi, Zhaoyan Gong, Zhiqiang Liu, Huajun Chen, and Wen Zhang. 2026c. What’s missing in screen-to-action? towards a ui-in-the-loop paradigm for multimodal gui reasoning. Preprint, arXiv:2604.06995. find
  57. Jared Kaplan, Sam McCandlish, Tom Henighan, Tom Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. Scaling laws for neural language models. In ICML.
  58. Xiaoyuan Li, Keqin Bao, Yubo Ma, Moxin Li, Wenjie Wang, Rui Men, Yichang Zhang, Fuli Feng, Dayiheng Liu, and Junyang Lin. 2025c. Mtr-bench: A comprehensive benchmark for multi-turn reasoning evaluation. arXiv preprint arXiv:2505.17123.
  59. Jihyung Kil, Zheda Mai, Justin Lee, Zihe Wang, Kerrie Cheng, Lemeng Wang, Ye Liu, Arpita Chowdhury, and Wei-Lun Chao. 2024. Compbench: A comparative reasoning benchmark for multimodal llms. find
  60. Zhimin Li, Jianwei Zhang, Qin Lin, Jiangfeng Xiong, Yanxin Long, Xinchi Deng, Yingfang Zhang, Xingchao Liu, Minbin Huang, Zedong Xiao, Dayou Chen, Jiajun He, Jiahao Li, Wenyue Li, Chen Zhang, Rongwei Quan, Jianxiang Lu, Jiabin Huang, Xiaoyan Yuan, and 26 others. 2024c. Hunyuan-dit: A powerful multi-…
  61. Seungone Kim, Jamin Shin, Yejin Cho, Joel Jang, Shayne Longpre, Hwaran Lee, Sangdoo Yun, Seongjin Shin, Sungdong Kim, James Thorne, and 1 others. 2023. Prometheus: Inducing fine-grained evaluation capability in language models. In The Twelfth International Conference on Learning Representations.
  62. Black Forest Labs. 2024. Flux. find
  63. Tian Liang, Zhiwei He, Wenxiang Jiao, Xing Wang, Yan Wang, Rui Wang, Yujiu Yang, Shuming Shi, and Zhaopeng Tu. 2024a. Encouraging divergent thinking in large language models through multi-agent debate. In Proceedings of the 2024 conference on empirical methods in natural language processing, pages 1…
  64. Weixin Liang, Lili Yu, Liang Luo, Srinivasan Iyer, Ning Dong, Chunting Zhou, Gargi Ghosh, Mike Lewis, Wen-tau Yih, Luke Zettlemoyer, and 1 others. 2024b. Mixture-of-transformers: A sparse and scalable architecture for multi-modal foundation models. arXiv preprint arXiv:2411.04996. find
  65. Honglin Lin, Zheng Liu, Yun Zhu, Chonghan Qin, Juekai Lin, Xiaoran Shang, Conghui He, Wentao Zhang, and Lijun Wu. 2026a. Mmfinereason: Closing the multimodal reasoning gap via open data-centric methods. arXiv preprint arXiv:2601.21821. — [arXiv:2601.21821](https://arxiv.org/abs/2601.21821) find
  66. Honglin Lin, Chonghan Qin, Zheng Liu, Qizhi Pei, Yu Li, Zhanping Zhong, Xin Gao, Yanfeng Wang, Conghui He, and Lijun Wu. 2026b. Scientific image synthesis: Benchmarking, methodologies, and downstream utility. arXiv preprint arXiv:2601.17027. — [arXiv:2601.17027](https://arxiv.org/abs/2601.17027) find
  67. Jiaye Lin, Yifu Guo, Yuzhen Han, Sen Hu, Ziyi Ni, Licheng Wang, Mingguang Chen, Hongzhang Liu, Ronghao Chen, Yangfan He, and 1 others. 2025. Se-agent: Self-evolution trajectory optimization in multi-step reasoning with llm-based agents. arXiv preprint arXiv:2508.02085. — [arXiv:2508.02085](https://arxiv.org/abs/2508.02085) find
  68. Hao Liu, Wilson Yan, Matei Zaharia, and Pieter Abbeel. 2024a. World model on million-length video and language with ringattention. arXiv preprint arXiv:2402.08268.
  69. Yuan Liu, Haodong Duan, Yuanhan Zhang, Bo Li, Songyang Zhang, Wangbo Zhao, Yike Yuan, Jiaqi Wang, Conghui He, Ziwei Liu, and 1 others. 2024b. Mmbench: Is your multi-modal model an all-around player? In European Conference on Computer Vision.
  70. Zheng Liu, Hao Liang, Xijie Huang, Wentao Xiong, Qinhan Yu, Linzhuang Sun, Chong Chen, Conghui He, Bin Cui, and Wentao Zhang. 2024c. Synthvlm: High-efficiency and high-quality synthetic data for vision language models. arXiv preprint arXiv:2407.20756, 3. — [arXiv:2407.20756](https://arxiv.org/abs/2407.20756) find
  71. Zheng Liu, Honglin Lin, Chonghan Qin, Xiaoyang Wang, Xin Gao, Yu Li, Mengzhang Cai, Yun Zhu, Zhanping Zhong, Qizhi Pei, and 1 others. 2026. Chartverse: Scaling chart reasoning via reliable programmatic synthesis from scratch. arXiv preprint arXiv:2601.13606.
  72. Zheng Liu, Mengjie Liu, Jingzhou Chen, Jingwei Xu, Bin Cui, Conghui He, and Wentao Zhang. 2025a. Fusion: Fully integration of vision-language representations for deep cross-modal understanding. arXiv preprint arXiv:2504.09925. — [arXiv:2504.09925](https://arxiv.org/abs/2504.09925) find
  73. Zheng Liu, Mengjie Liu, Siwei Wen, Mengzhang Cai, Bin Cui, Conghui He, and Wentao Zhang. 2025b. From uniform to heterogeneous: Tailoring policy optimization to every token’s nature. arXiv preprint arXiv:2509.16591. — [arXiv:2509.16591](https://arxiv.org/abs/2509.16591) find
  74. Zijun Liu, Peiyi Wang, Runxin Xu, Shirong Ma, Chong Ruan, Peng Li, Yang Liu, and Yu Wu. 2025c. Inference-time scaling for generalist reward modeling. arXiv preprint arXiv:2504.02495.
  75. Hongxu Ma, Kai Tian, Tao Zhang, Xuefeng Zhang, Han Zhou, Chunjie Chen, Han Li, Jihong Guan, and Shuigeng Zhou. 2024a. Generative regression based watch time prediction for short-video recommendation. arXiv preprint arXiv:2412.20211. — [arXiv:2412.20211](https://arxiv.org/abs/2412.20211) find
  76. Hongxu Ma, Han Zhou, Kai Tian, Xuefeng Zhang, Chunjie Chen, Han Li, Jihong Guan, and Shuigeng Zhou. 2026a. Gor: A unified and extensible generative framework for ordinal regression. In The Fourteenth International Conference on Learning Representations. find
  77. Kexin Ma, Ruochun Jin, Wang Haotian, Wang Xi, Huan Chen, Yuhua Tang, and Qian Wang. 2024b. Context-driven index trimming: A data quality perspective to enhancing precision of ralms. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 4886–4901. find
  78. Kexin Ma, Bojun Li, Yuhua Tang, Liting Sun, and Ruochun Jin. 2026b. Cast: Character-and-scene episodic memory for agents. Preprint, arXiv:2602.06051. — [arXiv:2602.06051](https://arxiv.org/abs/2602.06051) find
  79. Xueqi Ma, Shuo Yang, Yanbei Jiang, Shu Liu, Zhenzhen Liu, Jiayang Ao, Xingjun Ma, Sarah Monazam Erfani, and James Bailey. 2026c. Attention in space: Functional roles of vlm heads for spatial reasoning. arXiv preprint arXiv:2603.20662. — [arXiv:2603.20662](https://arxiv.org/abs/2603.20662) find
  80. Weijia Mao, Zhenheng Yang, and Mike Zheng Shou. 2025. Unirl: Self-improving unified multimodal models via supervised and reinforcement learning. arXiv preprint arXiv:2505.23380. — [arXiv:2505.23380](https://arxiv.org/abs/2505.23380) find
  81. Midjourney. 2025. midjourney v7. find
  82. Sumeet Ramesh Motwani, Chandler Smith, Rocktim Jyoti Das, Rafael Rafailov, Ivan Laptev, Philip HS Torr, Fabio Pizzati, Ronald Clark, and Christian Schroeder de Witt. 2024. Malt: Improving reasoning with multi-agent llm training. arXiv preprint arXiv:2412.01928. — [arXiv:2412.01928](https://arxiv.org/abs/2412.01928) find
  83. Yuwei Niu, Munan Ning, Mengren Zheng, Bin Lin, Peng Jin, Jiaqi Liao, Kunpeng Ning, Bin Zhu, and Li Yuan. 2025. Wise: A world knowledge-informed semantic evaluation for text-to-image generation. arXiv preprint arXiv:2503.07265. — [arXiv:2503.07265](https://arxiv.org/abs/2503.07265) find
  84. OpenAI. 2025. Introducing 4o image generation. find
  85. Xichen Pan, Satya Narayan Shukla, Aashu Singh, Zhuokai Zhao, Shlok Kumar Mishra, Jialiang Wang, Zhiyang Xu, Jiuhai Chen, Kunpeng Li, Felix Juefei-Xu, Ji Hou, and Saining Xie. 2025. Transfer between modalities with metaqueries. arXiv preprint arXiv:2504.06256. — [arXiv:2504.06256](https://arxiv.org/abs/2504.06256) find
  86. Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas Müller, Joe Penna, and Robin Rombach. 2024. Sdxl: Improving latent diffusion models for high-resolution image synthesis. In International Conference on Learning Representations.
  87. Yukun Qi, Yiming Zhao, Yu Zeng, Xikun Bao, Wenxuan Huang, Lin Chen, Zehui Chen, Jie Zhao, Zhongang Qi, and Feng Zhao. 2025. Vcr-bench: A comprehensive evaluation framework for video chain-of-thought reasoning. arXiv preprint arXiv:2504.07956. — [arXiv:2504.07956](https://arxiv.org/abs/2504.07956) find
  88. Qi Qin, Le Zhuo, Yi Xin, Ruoyi Du, Zhen Li, Bin Fu, Yiting Lu, Jiakang Yuan, Xinyue Li, Dongyang Liu, and 1 others. 2025. Lumina-image 2.0: A unified and efficient image generative framework. arXiv preprint arXiv:2503.21758. — [arXiv:2503.21758](https://arxiv.org/abs/2503.21758) find
  89. Liao Qu, Huichao Zhang, Yiheng Liu, Xu Wang, Yi Jiang, Yiming Gao, Hu Ye, Daniel K Du, Zehuan Yuan, and Xinglong Wu. 2024. Tokenflow: Unified image tokenizer for multimodal understanding and generation. arXiv preprint arXiv:2412.03069. — [arXiv:2412.03069](https://arxiv.org/abs/2412.03069) find
  90. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, and 1 others. 2019. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9. find
  91. Vyas Raina, Adian Liusie, and Mark Gales. 2024. Is llm-as-a-judge robust? investigating universal adversarial attacks on zero-shot llm assessment. arXiv preprint arXiv:2402.14016.
  92. Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. 2022. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125.
  93. Qingnan Ren, Shiting Huang, Zhen Fang, Zehui Chen, Lin Chen, Lijun Li, and Feng Zhao. 2026. Adora: Training reasoning models with dynamic advantage estimation on reinforcement learning. arXiv preprint arXiv:2602.10019. — [arXiv:2602.10019](https://arxiv.org/abs/2602.10019) find
  94. Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Björn Ommer. 2022. High-resolution image synthesis with latent diffusion models. In CVPR, pages 10684–10695.
  95. Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, and 1 others. 2022. Laion-5b: An open large-scale dataset for training next generation image-text models. Advances in neural information proce…
  96. Weijia Shi, Xiaochuang Han, Chunting Zhou, Weixin Liang, Xi Victoria Lin, Luke Zettlemoyer, and Lili Yu. 2024. Lmfusion: Adapting pretrained language models for multimodal generation. arXiv preprint arXiv:2412.15188. find
  97. Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2023. Reflexion: Language agents with verbal reinforcement learning. Advances in Neural Information Processing Systems, 36:8634–8652.
  98. David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, Laurent Sifre, Dharshan Kumaran, Thore Graepel, and 1 others. 2017. Mastering chess and shogi by self-play with a general reinforcement learning algorithm. arXiv preprint arXiv:1712.01815.
  99. Chameleon Team. 2024. Chameleon: Mixed-modal early-fusion foundation models. arXiv preprint arXiv:2405.09818.
  100. Aman Singh Thakur, Kartik Choudhary, Venkat Srinik Ramayapally, Sankaran Vaidyanathan, and Dieuwke Hupkes. 2025. Judging the judges: Evaluating alignment and vulnerabilities in llms-as-judges. In Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM 2 ), pages 404–430. find
  101. Rui Tian, Mingfei Gao, Mingze Xu, Jiaming Hu, Jiasen Lu, Zuxuan Wu, Yinfei Yang, and Afshin Dehghan. 2025. Unigen: Enhanced training & test-time strategies for unified multimodal understanding and generation. arXiv preprint arXiv:2505.14682. — [arXiv:2505.14682](https://arxiv.org/abs/2505.14682) find
  102. Shengbang Tong, David Fan, Jiachen Li, Yunyang Xiong, Xinlei Chen, Koustuv Sinha, Michael Rabbat, Yann LeCun, Saining Xie, and Zhuang Liu. 2025. Metamorph: Multimodal understanding and generation via instruction tuning. In Proceedings of the IEEE/CVF International Conference on Computer Vision, page… find
  103. Shengbang Tong, Zhuang Liu, Yuexiang Zhai, Yi Ma, Yann LeCun, and Saining Xie. 2024. Eyes wide shut? exploring the visual shortcomings of multimodal llms. In CVPR, pages 9568–9578.
  104. Chunwei Wang, Guansong Lu, Junwei Yang, Runhui Huang, Jianhua Han, Lu Hou, Wei Zhang, and Hang Xu. 2024a. Illume: Illuminating your llms to see, draw, and self-enhance. arXiv preprint arXiv:2412.06673. — [arXiv:2412.06673](https://arxiv.org/abs/2412.06673) find
  105. Eileen Wang, Hiba Arnaout, Dhita Pratama, Shuo Yang, Dangyang Liu, Jie Yang, Josiah Poon, Jeff Pan, and Caren Han. 2026a. Mmcomet: A large-scale multimodal commonsense knowledge graph for contextual reasoning. arXiv preprint arXiv:2603.01055. — [arXiv:2603.01055](https://arxiv.org/abs/2603.01055) find
  106. Junxi Wang, Te Sun, Jiayi Zhu, Junxian Li, Haowen Xu, Zichen Wen, Xuming Hu, Zhiyu Li, and Linfeng Zhang. 2026b. Streammeco: Long-term agent memory compression for efficient streaming video understanding. Preprint, arXiv:2604.09000.
  107. Junxi Wang, Yaxiong Wang, Lechao Cheng, and Zhun Zhong. 2025a. Fakesv-vlm: Taming vlm for detecting fake short-video news via progressive mixture-of-experts adapter. Preprint, arXiv:2508.19639. find
  108. Qiuchen Wang, Ruixue Ding, Yu Zeng, Zehui Chen, Lin Chen, Shihang Wang, Pengjun Xie, Fei Huang, and Feng Zhao. 2025b. Vrag-rl: Empower vision-perception-based rag for visually rich information understanding via iterative reasoning with reinforcement learning. arXiv preprint arXiv:2505.22019.
  109. 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
  110. Yibin Wang, Yuhang Zang, Hao Li, Cheng Jin, and Jiaqi Wang. 2025c. Unified reward model for multimodal understanding and generation. arXiv preprint arXiv:2503.05236. — [arXiv:2503.05236](https://arxiv.org/abs/2503.05236) find
  111. Zi-Han Wang, Lam Nguyen, Zhengyang Zhao, Mengyue Yang, Chengwei Qin, Yujiu Yang, and Linyi Yang. 2026c. Creativebench: Benchmarking and enhancing machine creativity via self-evolving challenges. arXiv preprint arXiv:2603.11863.
  112. Xinyu Wei, Jinrui Zhang, Zeqing Wang, Hongyang Wei, Zhen Guo, and Lei Zhang. 2025. Tiif-bench: How does your t2i model follow your instructions? Preprint, arXiv:2506.02161. — [arXiv:2506.02161](https://arxiv.org/abs/2506.02161) find
  113. Chenfei Wu, Jiahao Li, Jingren Zhou, Junyang Lin, Kaiyuan Gao, Kun Yan, Sheng-ming Yin, Shuai Bai, Xiao Xu, Yilei Chen, and 1 others. 2025a. Qwen-image technical report. arXiv preprint arXiv:2508.02324.
  114. Chengyue Wu, Xiaokang Chen, Zhiyu Wu, Yiyang Ma, Xingchao Liu, Zizheng Pan, Wen Liu, Zhenda Xie, Xingkai Yu, Chong Ruan, and 1 others. 2025b. Janus: Decoupling visual encoding for unified multimodal understanding and generation. In Proceedings of the Computer Vision and Pattern Recognition Conferenc…
  115. Shitao Xiao, Yueze Wang, Junjie Zhou, Huaying Yuan, Xingrun Xing, Ruiran Yan, Chaofan Li, Shuting Wang, Tiejun Huang, and Zheng Liu. 2025a. Omnigen: Unified image generation. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 13294–13304. find
  116. Xi Xiao, Chenrui Ma, Yunbei Zhang, Chen Liu, Zhux-uanzi Wang, Yanshu Li, Lin Zhao, Guosheng Hu, Tianyang Wang, and Hao Xu. 2026. Not all directions matter: Toward structured and task-aware low-rank adaptation. arXiv preprint arXiv:2603.14228. — [arXiv:2603.14228](https://arxiv.org/abs/2603.14228) find
  117. Xi Xiao, Yunbei Zhang, Xingjian Li, Tianyang Wang, Xiao Wang, Yuxiang Wei, Jihun Hamm, and Min Xu. 2025b. Visual instance-aware prompt tuning. In 33rd ACM International Conference on Multimedia, MM 2025, pages 2880–2889. Association for Computing Machinery, Inc. find
  118. Xi Xiao, Yunbei Zhang, Lin Zhao, Yiyang Liu, Xiaoying Liao, Zheda Mai, Xingjian Li, Xiao Wang, Hao Xu, Jihun Hamm, and 1 others. 2025c. Prompt-based adaptation in large-scale vision models: A survey. arXiv preprint arXiv:2510.13219. — [arXiv:2510.13219](https://arxiv.org/abs/2510.13219) find
  119. Enze Xie, Junsong Chen, Yuyang Zhao, Jincheng Yu, Ligeng Zhu, Chengyue Wu, Yujun Lin, Zhekai Zhang, Muyang Li, Junyu Chen, and 1 others. 2025a. Sana 1.5: Efficient scaling of training-time and inference-time compute in linear diffusion transformer. arXiv preprint arXiv:2501.18427. — [arXiv:2501.18427](https://arxiv.org/abs/2501.18427) find
  120. Ji Xie, Trevor Darrell, Luke Zettlemoyer, and XuDong Wang. 2025b. Reconstruction alignment improves unified multimodal models. arXiv preprint arXiv:2509.07295. find
  121. Jinheng Xie, Weijia Mao, Zechen Bai, David Junhao Zhang, Weihao Wang, Kevin Qinghong Lin, Yuchao Gu, Zhijie Chen, Zhenheng Yang, and Mike Zheng Shou. 2024. 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
  122. Jinheng Xie, Zhenheng Yang, and Mike Zheng Shou. 2025c. Show-o2: Improved native unified multimodal models. arXiv preprint arXiv:2506.15564. — [arXiv:2506.15564](https://arxiv.org/abs/2506.15564) find
  123. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, and 1 others. 2025a. Qwen3 technical report. arXiv preprint arXiv:2505.09388.
  124. Shuo Yang, Caren Han, Yihao Ding, Shuhe Wang, and Eduard Hovy. 2026. Tooltree: Efficient llm tool planning via dual-feedback monte carlo tree search and bidirectional pruning. In The Fourteenth International Conference on Learning Representations, volume 3. find
  125. Shuo Yang, Caren Han, Siwen Luo, and Eduard Hovy. 2025b. Magic-vqa: Multimodal and grounded inference with commonsense knowledge for visual question answering. In Findings of the Association for Computational Linguistics: ACL 2025, pages 16967– 16986. find
  126. Wenhao Yu, Zhenwen Liang, Chengsong Huang, Kishan Panaganti, Tianqing Fang, Haitao Mi, and Dong Yu. 2025. Guided self-evolving llms with minimal human supervision. arXiv preprint arXiv:2512.02472. — [arXiv:2512.02472](https://arxiv.org/abs/2512.02472) find
  127. Weizhe Yuan, Richard Yuanzhe Pang, Kyunghyun Cho, Xian Li, Sainbayar Sukhbaatar, Jing Xu, and Jason E Weston. 2024. Self-rewarding language models. In Forty-first International Conference on Machine Learning. find
  128. 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 CVPR.
  129. Yu Zeng, Wenxuan Huang, Zhen Fang, Shuang Chen, Yufan Shen, Yishuo Cai, Xiaoman Wang, Zhenfei Yin, Lin Chen, Zehui Chen, and 1 others. 2026. Vision-deepresearch benchmark: Rethinking visual and textual search for multimodal large language models. arXiv preprint arXiv:2602.02185. — [arXiv:2602.02185](https://arxiv.org/abs/2602.02185) find
  130. Yu Zeng, Wenxuan Huang, Shiting Huang, Xikun Bao, Yukun Qi, Yiming Zhao, Qiuchen Wang, Lin Chen, Zehui Chen, Huaian Chen, and 1 others. 2025a. Agentic jigsaw interaction learning for enhancing visual perception and reasoning in vision-language models. arXiv preprint arXiv:2510.01304. find
  131. Yu Zeng, Yukun Qi, Yiming Zhao, Xikun Bao, Lin Chen, Zehui Chen, Shiting Huang, Jie Zhao, and Feng Zhao. 2025b. Enhancing large vision-language models with ultra-detailed image caption generation. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 26703–… find
  132. Huanyu Zhang, Xuehai Bai, Chengzu Li, Chen Liang, Haochen Tian, Haodong Li, Ruichuan An, Yifan Zhang, Anna Korhonen, Zhang Zhang, and 1 others. 2026a. How well do models follow visual instructions? vibe: A systematic benchmark for visual instruction-driven image editing. arXiv preprint arXiv:2602.01… — [arXiv:2602.01851](https://arxiv.org/abs/2602.01851) find
  133. Qianchi Zhang, Hainan Zhang, Liang Pang, Yongxin Tong, Hongwei Zheng, and Zhiming Zheng. 2025a. Less is more: Compact clue selection for efficient retrieval-augmented generation reasoning. arXiv preprint arXiv:2502.11811. — [arXiv:2502.11811](https://arxiv.org/abs/2502.11811) find
  134. Qianchi Zhang, Hainan Zhang, Liang Pang, Hongwei Zheng, and Zhiming Zheng. 2026b. Stable-rag: Mitigating retrieval-permutation-induced hallucinations in retrieval-augmented generation. arXiv preprint arXiv:2601.02993.
  135. Wenyuan Zhang, Xinghua Zhang, Haiyang Yu, Shuaiyi Nie, Bingli Wu, Juwei Yue, Tingwen Liu, and Yongbin Li. 2026c. Expseek: Self-triggered experience seeking for web agents. Preprint, arXiv:2601.08605.
  136. Xinglang Zhang, Yunyao Zhang, ZeLiang Chen, Junqing Yu, Wei Yang, and Zikai Song. 2026d. Logical phase transitions: Understanding collapse in llm logical reasoning. Preprint, arXiv:2601.02902.
  137. Yunyao Zhang, Yihao Ai, Zuocheng Ying, Qirui Mi, Junqing Yu, Wei Yang, and Zikai Song. 2026e. Coupling macro dynamics and micro states for long-horizon social simulation. Preprint, arXiv:2604.05516. — [arXiv:2604.05516](https://arxiv.org/abs/2604.05516) find
  138. Yunyao Zhang, Zikai Song, Hang Zhou, Wenfeng Ren, Yi-Ping Phoebe Chen, Junqing Yu, and Wei Yang. 2025b. ga − s 3 : Comprehensive social network simulation with group agents. In Findings of the Association for Computational Linguistics: ACL 2025, pages 8950–8970, Vienna, Austria. Association for Comp… find
  139. Yunyao Zhang, Xinglang Zhang, Junxi Sheng, Wenbing Li, Junqing Yu, Yi-Ping Phoebe Chen, Wei Yang, and Zikai Song. 2026f. Semantic-aware logical reasoning via a semiotic framework. Preprint, arXiv:2509.24765.
  140. Andrew Zhao, Yiran Wu, Yang Yue, Tong Wu, Quentin Xu, Matthieu Lin, Shenzhi Wang, Qingyun Wu, Zilong Zheng, and Gao Huang. 2025a. Absolute zero: Reinforced self-play reasoning with zero data. arXiv preprint arXiv:2505.03335.
  141. 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
  142. Pengxiang Zhao, Guangyi Liu, Yaozhen Liang, Weiqing He, Zhengxi Lu, Yuehao Huang, Yaxuan Guo, Kexin Zhang, Hao Wang, Liang Liu, and 1 others. 2025b. Mas-bench: A unified benchmark for shortcut-augmented hybrid mobile gui agents. arXiv preprint arXiv:2509.06477.
  143. Xiangyu Zhao, Peiyuan Zhang, Kexian Tang, Xiaorong Zhu, Hao Li, Wenhao Chai, Zicheng Zhang, Renqiu Xia, Guangtao Zhai, Junchi Yan, and 1 others. 2025c. Envisioning beyond the pixels: Benchmarking reasoning-informed visual editing. arXiv preprint arXiv:2504.02826. — [arXiv:2504.02826](https://arxiv.org/abs/2504.02826) find
  144. Yiming Zhao, Yu Zeng, Yukun Qi, YaoYang Liu, Lin Chen, Zehui Chen, Xikun Bao, Jie Zhao, and Feng Zhao. 2025d. V2p-bench: Evaluating video-language understanding with visual prompts for better human-model interaction. arXiv preprint arXiv:2503.17736. — [arXiv:2503.17736](https://arxiv.org/abs/2503.17736) find
  145. Wang Zhenyu, Xie Enze, Li Aoxue, Wang Zhongdao, Liu Xihui, and Li Zhenguo. 2024. Divide and conquer: Language models can plan and self-correct for compositional text-to-image generation. IEEE Conference on Computer Vision and Pattern Recognition. find
  146. Chunting Zhou, Lili Yu, Arun Babu, Kushal Tirumala, Michihiro Yasunaga, Leonid Shamis, Jacob Kahn, Xuezhe Ma, Luke Zettlemoyer, and Omer Levy. 2024a. Transfusion: Predict the next token and diffuse images with one multi-modal model. arXiv preprint arXiv:2408.11039.
  147. Yiyang Zhou, Zhiyuan Fan, Dongjie Cheng, Sihan Yang, Zhaorun Chen, Chenhang Cui, Xiyao Wang, Yun Li, Linjun Zhang, and Huaxiu Yao. 2024b. Calibrated self-rewarding vision language models. Advances in Neural Information Processing Systems, 37:51503– 51531. find
  148. Le Zhuo, Ruoyi Du, Han Xiao, Yangguang Li, Dongyang Liu, Rongjie Huang, Wenze Liu, Xiangyang Zhu, Fu-Yun Wang, Zhanyu Ma, and 1 others. 2024. Lumina-next: Making lumina-t2x stronger and faster with next-dit. Advances in Neural Information Processing Systems, 37:131278–131315. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/fang-2026-unicorn-self-improving-unified-multimodal/