{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T21:13:18Z","timestamp":1788556398967,"version":"build-2803163510"},"publisher-location":"New York, NY, USA","reference-count":78,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3817654","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:43Z","timestamp":1786036543000},"page":"1686-1697","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-rewards"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5599-6425","authenticated-orcid":false,"given":"Jixiang","family":"Hong","sequence":"first","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0007-5454","authenticated-orcid":false,"given":"Yiran","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3287-0740","authenticated-orcid":false,"given":"Guanzhong","family":"Wang","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7575-2299","authenticated-orcid":false,"given":"Yi","family":"Liu","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9777-9676","authenticated-orcid":false,"given":"Ji-Rong","family":"Wen","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3356-6823","authenticated-orcid":false,"given":"Rui","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Anthropic. 2024. Introducing the next generation of Claude. (2024). https:\/\/www.anthropic.com\/news\/claude-3-family"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02129"},{"key":"e_1_3_2_1_4_1","unstructured":"Jinze Bai Shuai Bai Shusheng Yang Shijie Wang Sinan Tan Peng Wang Junyang Lin Chang Zhou and Jingren Zhou. 2023. Qwen-VL: A Versatile Vision-Language Model for Understanding Localization Text Reading and Beyond. arXiv:2308.12966 [cs.CV] https:\/\/arxiv.org\/abs\/2308.12966"},{"key":"e_1_3_2_1_5_1","unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Shijie Wang Jun Tang Humen Zhong Yuanzhi Zhu Mingkun Yang Zhaohai Li Jianqiang Wan Pengfei Wang Wei Ding Zheren Fu Yiheng Xu Jiabo Ye Xi Zhang Tianbao Xie Zesen Cheng Hang Zhang Zhibo Yang Haiyang Xu and Junyang Lin. 2025. Qwen2.5-VL Technical Report. arXiv:2502.13923 [cs.CV] https:\/\/arxiv.org\/abs\/2502.13923"},{"key":"e_1_3_2_1_6_1","unstructured":"James Betker Gabriel Goh Li Jing Tim Brooks Jianfeng Wang Linjie Li Long Ouyang Juntang Zhuang Joyce Lee Yufei Guo et al. 2023. Improving image generation with better captions. Computer Science. https:\/\/cdn.openai.com\/papers\/dall-e-3.pdf Vol. 2 3 (2023) 8."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"e_1_3_2_1_8_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Chen Junsong","year":"2024","unstructured":"Junsong Chen, YU Jincheng, GE Chongjian, Lewei Yao, Enze Xie, Zhongdao Wang, James Kwok, Ping Luo, Huchuan Lu, and Zhenguo Li. 2024a. PixArt-$alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_9_1","volume-title":"Janus-pro: Unified multimodal understanding and generation with data and model scaling. arXiv preprint arXiv:2501.17811","author":"Chen Xiaokang","year":"2025","unstructured":"Xiaokang Chen, Zhiyu Wu, Xingchao Liu, Zizheng Pan, Wen Liu, Zhenda Xie, Xingkai Yu, and Chong Ruan. 2025. Janus-pro: Unified multimodal understanding and generation with data and model scaling. arXiv preprint arXiv:2501.17811 (2025)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"e_1_3_2_1_12_1","volume-title":"High Fidelity Neural Audio Compression. Transactions on Machine Learning Research","author":"D\u00e9fossez Alexandre","year":"2023","unstructured":"Alexandre D\u00e9fossez, Jade Copet, Gabriel Synnaeve, and Yossi Adi. 2023. High Fidelity Neural Audio Compression. Transactions on Machine Learning Research (2023). https:\/\/openreview.net\/forum?id=ivCd8z8zR2"},{"key":"e_1_3_2_1_13_1","volume-title":"Emerging Properties in Unified Multimodal Pretraining. arXiv preprint arXiv:2505.14683","author":"Deng Chaorui","year":"2025","unstructured":"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. 2025. Emerging Properties in Unified Multimodal Pretraining. arXiv preprint arXiv:2505.14683 (2025)."},{"key":"e_1_3_2_1_14_1","volume-title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis. In International Conference on Machine Learning. PMLR, 12606-12633","author":"Esser Patrick","year":"2024","unstructured":"Patrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari, Jonas M\u00fcller, Harry Saini, Yam Levi, Dominik Lorenz, Axel Sauer, Frederic Boesel, Dustin Podell, Tim Dockhorn, Zion English, and Robin Rombach. 2024. Scaling Rectified Flow Transformers for High-Resolution Image Synthesis. In International Conference on Machine Learning. PMLR, 12606-12633."},{"key":"e_1_3_2_1_15_1","volume-title":"Taming Transformers for High-Resolution Image Synthesis. In 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 12868-12878","author":"Esser Patrick","year":"2021","unstructured":"Patrick Esser, Robin Rombach, and Bjorn Ommer. 2021. Taming Transformers for High-Resolution Image Synthesis. In 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 12868-12878."},{"key":"e_1_3_2_1_16_1","volume-title":"Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=PUIqjT4rzq7","author":"Feng Weixi","year":"2023","unstructured":"Weixi Feng, Xuehai He, Tsu-Jui Fu, Varun Jampani, Arjun Reddy Akula, Pradyumna Narayana, Sugato Basu, Xin Eric Wang, and William Yang Wang. 2023. Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=PUIqjT4rzq7"},{"key":"e_1_3_2_1_17_1","volume-title":"Seed-x: Multimodal models with unified multi-granularity comprehension and generation. arXiv preprint arXiv:2404.14396","author":"Ge Yuying","year":"2024","unstructured":"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 (2024)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2270"},{"key":"e_1_3_2_1_19_1","volume-title":"Garnett (Eds.)","volume":"29","author":"He Di","year":"2016","unstructured":"Di He, Yingce Xia, Tao Qin, Liwei Wang, Nenghai Yu, Tie-Yan Liu, and Wei-Ying Ma. 2016. Dual Learning for Machine Translation. In Advances in Neural Information Processing Systems, D. Lee, M. Sugiyama, U. Luxburg, I. Guyon, and R. Garnett (Eds.), Vol. 29. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2016\/file\/5b69b9cb83065d403869739ae7f0995e-Paper.pdf"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3443"},{"key":"e_1_3_2_1_21_1","volume-title":"Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback. arXiv:2412.15838 [cs.AI] https:\/\/arxiv.org\/abs\/2412.15838","author":"Ji Jiaming","year":"2024","unstructured":"Jiaming Ji, Jiayi Zhou, Hantao Lou, Boyuan Chen, Donghai Hong, Xuyao Wang, Wenqi Chen, Kaile Wang, Rui Pan, Jiahao Li, Mohan Wang, Josef Dai, Tianyi Qiu, Hua Xu, Dong Li, Weipeng Chen, Jun Song, Bo Zheng, and Yaodong Yang. 2024. Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback. arXiv:2412.15838 [cs.AI] https:\/\/arxiv.org\/abs\/2412.15838"},{"key":"e_1_3_2_1_22_1","first-page":"39856","volume-title":"Advances in Neural Information Processing Systems","volume":"38","author":"Ziyu Guo Dongzhi JIANG","year":"2025","unstructured":"Dongzhi JIANG, Ziyu Guo, Renrui Zhang, ZHUOFAN ZONG, Hao Li, Le Zhuo, Shilin Yan, Pheng-Ann Heng, and Hongsheng Li. 2025. T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT. In Advances in Neural Information Processing Systems, Vol. 38. Curran Associates, Inc., 39856-39890."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2425"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.52202\/085713-0205"},{"key":"e_1_3_2_1_25_1","unstructured":"Black Forest Labs. 2024. FLUX. https:\/\/github.com\/black-forest-labs\/flux."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"e_1_3_2_1_27_1","volume-title":"LLaVA-OneVision: Easy Visual Task Transfer. Transactions on Machine Learning Research","author":"Li Bo","year":"2025","unstructured":"Bo Li, Yuanhan Zhang, Dong Guo, Renrui Zhang, Feng Li, Hao Zhang, Kaichen Zhang, Peiyuan Zhang, Yanwei Li, Ziwei Liu, and Chunyuan Li. 2025b. LLaVA-OneVision: Easy Visual Task Transfer. Transactions on Machine Learning Research (2025). https:\/\/openreview.net\/forum?id=zKv8qULV6n"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.52202\/085713-3511"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"e_1_3_2_1_30_1","first-page":"740","volume-title":"Switzerland","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, 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. Springer, 740-755."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"e_1_3_2_1_32_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2023), 34892-34916."},{"key":"e_1_3_2_1_33_1","volume-title":"World model on million-length video and language with ringattention. arXiv e-prints","author":"Liu Hao","year":"2024","unstructured":"Hao Liu, Wilson Yan, Matei Zaharia, and Pieter Abbeel. 2024c. World model on million-length video and language with ringattention. arXiv e-prints (2024), arXiv-2402."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.52202\/085713-1362"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"e_1_3_2_1_36_1","volume-title":"European Conference on Computer Vision. 216-233","author":"Liu Yuan","year":"2024","unstructured":"Yuan Liu, Haodong Duan, Yuanhan Zhang, Bo Li, Songyang Zhang, Wangbo Zhao, Yike Yuan, Jiaqi Wang, Conghui He, Ziwei Liu, et al., 2024a. MMBench: Is Your Multi-modal Model an All-Around Player?. In European Conference on Computer Vision. 216-233."},{"key":"e_1_3_2_1_37_1","unstructured":"Haoyu Lu Wen Liu Bo Zhang Bingxuan Wang Kai Dong Bo Liu Jingxiang Sun Tongzheng Ren Zhuoshu Li Hao Yang et al. 2024. Deepseek-vl: towards real-world vision-language understanding. arXiv preprint arXiv:2403.05525 (2024)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1882"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3946"},{"key":"e_1_3_2_1_40_1","volume-title":"WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation. arXiv preprint arXiv:2503.07265","author":"Niu Yuwei","year":"2025","unstructured":"Yuwei Niu, Munan Ning, Mengren Zheng, Weiyang Jin, Bin Lin, Peng Jin, Jiaqi Liao, Kunpeng Ning, Chaoran Feng, Bin Zhu, and Li Yuan. 2025. WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation. arXiv preprint arXiv:2503.07265 (2025)."},{"key":"e_1_3_2_1_41_1","volume-title":"Object-centric Self-improving Preference Optimization for Text-to-Image Generation. arXiv preprint arXiv:2506.02015","author":"Oh Yoonjin","year":"2025","unstructured":"Yoonjin Oh, Yongjin Kim, Hyomin Kim, Donghwan Chi, and Sungwoong Kim. 2025. Object-centric Self-improving Preference Optimization for Text-to-Image Generation. arXiv preprint arXiv:2506.02015 (2025)."},{"key":"e_1_3_2_1_42_1","volume-title":"https:\/\/cdn.openai.com\/papers\/GPTV_System_Card.pdf","author":"System Card AI.","year":"2023","unstructured":"OpenAI. 2023. GPT-4V(ision) System Card. (2023). https:\/\/cdn.openai.com\/papers\/GPTV_System_Card.pdf"},{"key":"e_1_3_2_1_43_1","volume-title":"European Conference on Computer Vision. Springer, 395-413","author":"Ouali Yassine","year":"2024","unstructured":"Yassine Ouali, Adrian Bulat, Brais Martinez, and Georgios Tzimiropoulos. 2024. Clip-dpo: Vision-language models as a source of preference for fixing hallucinations in lvlms. In European Conference on Computer Vision. Springer, 395-413."},{"key":"e_1_3_2_1_44_1","volume-title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis. In International Conference on Learning Representations","volume":"2024","author":"Podell Dustin","year":"2024","unstructured":"Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas M\u00fcller, Joe Penna, and Robin Rombach. 2024. SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis. In International Conference on Learning Representations, Vol. 2024. 1862-1874."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01724"},{"key":"e_1_3_2_1_46_1","first-page":"8748","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning, Vol. 139. PMLR, 8748-8763."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2338"},{"key":"e_1_3_2_1_48_1","volume-title":"Hierarchical Text-Conditional Image Generation with CLIP Latents. arXiv preprint arXiv:2204.06125","author":"Ramesh Aditya","year":"2022","unstructured":"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 (2022)."},{"key":"e_1_3_2_1_49_1","volume-title":"High-Resolution Image Synthesis with Latent Diffusion Models. In 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 10674-10685","author":"Rombach Robin","year":"2022","unstructured":"Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Bj\u00f6rn Ommer. 2022. High-Resolution Image Synthesis with Latent Diffusion Models. In 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 10674-10685."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1009"},{"key":"e_1_3_2_1_51_1","volume-title":"Deepseekmath: Pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300","author":"Shao Zhihong","year":"2024","unstructured":"Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, Y Wu, et al., 2024. Deepseekmath: Pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300 (2024)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.188"},{"key":"e_1_3_2_1_53_1","volume-title":"The Fourteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=pG0WTde3pR","author":"Shi Qingyu","year":"2026","unstructured":"Qingyu Shi, Jinbin Bai, Zhuoran Zhao, Wenhao Chai, Kaidong Yu, Jianzong Wu, Shuangyong Song, Yunhai Tong, Xiangtai Li, Xuelong Li, and Shuicheng YAN. 2026. Beyond Text-to-Image: Liberating Generation with a Unified Discrete Diffusion Model. In The Fourteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=pG0WTde3pR"},{"key":"e_1_3_2_1_54_1","volume-title":"Proceedings of the 33rd ACM International Conference on Multimedia. 12199-12208","author":"Wan Renjie","year":"2025","unstructured":"Qi Song, Ziyuan Luo, Ka Chun Cheung, Simon See, and Renjie Wan. 2025. Align 3D Representation and Text Embedding for 3D Content Personalization. In Proceedings of the 33rd ACM International Conference on Multimedia. 12199-12208."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2161"},{"key":"e_1_3_2_1_56_1","volume-title":"Autoregressive model beats diffusion: Llama for scalable image generation. arXiv preprint arXiv:2406.06525","author":"Sun Peize","year":"2024","unstructured":"Peize Sun, Yi Jiang, Shoufa Chen, Shilong Zhang, Bingyue Peng, Ping Luo, and Zehuan Yuan. 2024b. Autoregressive model beats diffusion: Llama for scalable image generation. arXiv preprint arXiv:2406.06525 (2024)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01365"},{"key":"e_1_3_2_1_58_1","volume-title":"Emu: Generative Pretraining in Multimodality. In The Twelfth International Conference on Learning Representations.","author":"Sun Quan","year":"2024","unstructured":"Quan Sun, Qiying Yu, Yufeng Cui, Fan Zhang, Xiaosong Zhang, Yueze Wang, Hongcheng Gao, Jingjing Liu, Tiejun Huang, and Xinlong Wang. 2024c. Emu: Generative Pretraining in Multimodality. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_59_1","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems. 6309-6318","author":"van den Oord Aaron","year":"2017","unstructured":"Aaron van den Oord, Oriol Vinyals, and Koray Kavukcuoglu. 2017. Neural discrete representation learning. In Proceedings of the 31st International Conference on Neural Information Processing Systems. 6309-6318."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02007"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.52202\/085713-2720"},{"key":"e_1_3_2_1_62_1","unstructured":"Junke Wang Zhi Tian Xun Wang Xinyu Zhang Weilin Huang Zuxuan Wu and Yu-Gang Jiang. 2025c. SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through Pretraining SFT and RL. arXiv:2504.11455 [cs.CV] https:\/\/arxiv.org\/abs\/2504.11455"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-10041-x"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01210"},{"key":"e_1_3_2_1_65_1","first-page":"53366","volume-title":"Proceedings of the 41st International Conference on Machine Learning","volume":"235","author":"Wu Shengqiong","year":"2024","unstructured":"Shengqiong Wu, Hao Fei, Leigang Qu, Wei Ji, and Tat-Seng Chua. 2024b. NExT-GPT: Any-to-Any Multimodal LLM. In Proceedings of the 41st International Conference on Machine Learning, Vol. 235. PMLR, 53366-53397."},{"key":"e_1_3_2_1_66_1","first-page":"93620","volume-title":"International Conference on Learning Representations","volume":"2025","author":"Wu Yecheng","year":"2025","unstructured":"Yecheng Wu, Zhuoyang Zhang, Junyu Chen, Haotian Tang, Dacheng Li, Yunhao Fang, Ligeng Zhu, Enze Xie, Hongxu Yin, Li Yi, Song Han, and Yao Lu. 2025b. VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation. In International Conference on Learning Representations, Vol. 2025. 93620-93638."},{"key":"e_1_3_2_1_67_1","unstructured":"Zhiyu Wu Xiaokang Chen Zizheng Pan Xingchao Liu Wen Liu Damai Dai Huazuo Gao Yiyang Ma Chengyue Wu Bingxuan Wang et al. 2024a. Deepseek-vl2: Mixture-of-experts vision-language models for advanced multimodal understanding. arXiv preprint arXiv:2412.10302 (2024)."},{"key":"e_1_3_2_1_68_1","volume-title":"Proceedings of the 34th International Conference on Machine Learning. PMLR, 3789-3798","author":"Xia Yingce","year":"2017","unstructured":"Yingce Xia, Tao Qin, Wei Chen, Jiang Bian, Nenghai Yu, and Tie-Yan Liu. 2017. Dual Supervised Learning. In Proceedings of the 34th International Conference on Machine Learning. PMLR, 3789-3798."},{"key":"e_1_3_2_1_69_1","first-page":"28240","volume-title":"International Conference on Learning Representations","volume":"2025","author":"Xie Jinheng","year":"2025","unstructured":"Jinheng Xie, Weijia Mao, Zechen Bai, David Junhao Zhang, Weihao Wang, Kevin Qinghong Lin, Yuchao Gu, Zhijie Chen, Zhenheng Yang, and Mike Zheng Shou. 2025. Show-o: One Single Transformer to Unify Multimodal Understanding and Generation. In International Conference on Learning Representations, Vol. 2025. 28240-28264."},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.52202\/085713-4636"},{"key":"e_1_3_2_1_71_1","volume-title":"X-vila: Cross-modality alignment for large language model. arXiv preprint arXiv:2405.19335","author":"Ye Hanrong","year":"2024","unstructured":"Hanrong Ye, De-An Huang, Yao Lu, Zhiding Yu, Wei Ping, Andrew Tao, Jan Kautz, Song Han, Dan Xu, Pavlo Molchanov, et al., 2024. X-vila: Cross-modality alignment for large language model. arXiv preprint arXiv:2405.19335 (2024)."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-6110"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.521"},{"key":"e_1_3_2_1_74_1","volume-title":"Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models. In The Thirteenth International Conference on Learning Representations.","author":"Zhang Ce","year":"2025","unstructured":"Ce Zhang, Zifu Wan, Zhehan Kan, Martin Q. Ma, Simon Stepputtis, Deva Ramanan, Russ Salakhutdinov, Louis-Philippe Morency, Katia P. Sycara, and Yaqi Xie. 2025. Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME59968.2025.11209377"},{"key":"e_1_3_2_1_76_1","first-page":"6446","volume-title":"Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model. In International Conference on Learning Representations","volume":"2025","author":"Zhou Chunting","year":"2025","unstructured":"Chunting Zhou, Lili Yu, Arun Babu, Kushal Tirumala, Michihiro Yasunaga, Leonid Shamis, Jacob Kahn, Xuezhe Ma, Luke Zettlemoyer, and Omer Levy. 2025. Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model. In International Conference on Learning Representations, Vol. 2025. 6446-6469."},{"key":"e_1_3_2_1_77_1","first-page":"8","volume-title":"International Conference on Learning Representations","volume":"2024","author":"Zhu Deyao","year":"2024","unstructured":"Deyao Zhu, jun chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2024. MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models. In International Conference on Learning Representations, Vol. 2024. 18378-18394."},{"key":"e_1_3_2_1_78_1","volume-title":"Proceedings of the IEEE International Conference on Computer Vision. 2223-2232","author":"Zhu Jun-Yan","unstructured":"Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei A. Efros. 2017. Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks. In Proceedings of the IEEE International Conference on Computer Vision. 2223-2232."}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3770855.3817654","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T20:29:37Z","timestamp":1788553777000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3817654"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":78,"alternative-id":["10.1145\/3770855.3817654","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3817654","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}