{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:56:46Z","timestamp":1783439806193,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680610","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"4533-4542","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["TreeReward: Improve Diffusion Model via Tree-Structured Feedback Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6914-9969","authenticated-orcid":false,"given":"Jiacheng","family":"Zhang","sequence":"first","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9507-2062","authenticated-orcid":false,"given":"Jie","family":"Wu","sequence":"additional","affiliation":[{"name":"ByteDance, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8888-512X","authenticated-orcid":false,"given":"Huafeng","family":"Kuang","sequence":"additional","affiliation":[{"name":"ByteDance, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0432-4606","authenticated-orcid":false,"given":"Haiming","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong, Shenzhen, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6052-6557","authenticated-orcid":false,"given":"Yuxi","family":"Ren","sequence":"additional","affiliation":[{"name":"ByteDance, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5040-4618","authenticated-orcid":false,"given":"Weifeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2319-2749","authenticated-orcid":false,"given":"Manlin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8258-1243","authenticated-orcid":false,"given":"Xuefeng","family":"Xiao","sequence":"additional","affiliation":[{"name":"ByteDance, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2486-2890","authenticated-orcid":false,"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Yuntao Bai Saurav Kadavath Sandipan Kundu Amanda Askell Jackson Kernion Andy Jones Anna Chen Anna Goldie Azalia Mirhoseini Cameron McKinnon Carol Chen Catherine Olsson Christopher Olah Danny Hernandez Dawn Drain Deep Ganguli Dustin Li Eli Tran-Johnson Ethan Perez Jamie Kerr Jared Mueller Jeffrey Ladish Joshua Landau Kamal Ndousse Kamile Lukosuite Liane Lovitt Michael Sellitto Nelson Elhage Nicholas Schiefer Noemi Mercado Nova DasSarma Robert Lasenby Robin Larson Sam Ringer Scott Johnston Shauna Kravec Sheer El Showk Stanislav Fort Tamera Lanham Timothy Telleen-Lawton Tom Conerly Tom Henighan Tristan Hume Samuel R. Bowman Zac Hatfield-Dodds Ben Mann Dario Amodei Nicholas Joseph Sam McCandlish Tom Brown and Jared Kaplan. 2022. Constitutional AI: Harmlessness from AI Feedback. arxiv: 2212.08073 [cs.CL]"},{"key":"e_1_3_2_1_2_1","unstructured":"Kevin Black Michael Janner Yilun Du Ilya Kostrikov and Sergey Levine. 2023. Training Diffusion Models with Reinforcement Learning. arxiv: 2305.13301 [cs.LG]"},{"key":"e_1_3_2_1_3_1","volume-title":"ID-Aligner: Enhancing Identity-Preserving Text-to-Image Generation with Reward Feedback Learning. arXiv preprint arXiv:2404.15449","author":"Chen Weifeng","year":"2024","unstructured":"Weifeng Chen, Jiacheng Zhang, Jie Wu, Hefeng Wu, Xuefeng Xiao, and Liang Lin. 2024. ID-Aligner: Enhancing Identity-Preserving Text-to-Image Generation with Reward Feedback Learning. arXiv preprint arXiv:2404.15449 (2024)."},{"key":"e_1_3_2_1_4_1","unstructured":"Prafulla Dhariwal and Alex Nichol. 2021. Diffusion Models Beat GANs on Image Synthesis. arxiv: 2105.05233 [cs.LG]"},{"key":"e_1_3_2_1_5_1","first-page":"19822","article-title":"Cogview: Mastering text-to-image generation via transformers","volume":"34","author":"Ding Ming","year":"2021","unstructured":"Ming Ding, Zhuoyi Yang, Wenyi Hong, Wendi Zheng, Chang Zhou, Da Yin, Junyang Lin, Xu Zou, Zhou Shao, Hongxia Yang, et al. 2021. Cogview: Mastering text-to-image generation via transformers. Advances in Neural Information Processing Systems, Vol. 34 (2021), 19822--19835.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_6_1","volume-title":"Raft: Reward ranked finetuning for generative foundation model alignment. arXiv preprint arXiv:2304.06767","author":"Dong Hanze","year":"2023","unstructured":"Hanze Dong, Wei Xiong, Deepanshu Goyal, Rui Pan, Shizhe Diao, Jipeng Zhang, Kashun Shum, and Tong Zhang. 2023. Raft: Reward ranked finetuning for generative foundation model alignment. arXiv preprint arXiv:2304.06767 (2023)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"e_1_3_2_1_10_1","volume-title":"Ronan Le Bras, and Yejin Choi","author":"Hessel Jack","year":"2021","unstructured":"Jack Hessel, Ari Holtzman, Maxwell Forbes, Ronan Le Bras, and Yejin Choi. 2021. Clipscore: A reference-free evaluation metric for image captioning. arXiv preprint arXiv:2104.08718 (2021)."},{"key":"e_1_3_2_1_11_1","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-Free Diffusion Guidance. arxiv: 2207.12598 [cs.LG]"},{"key":"e_1_3_2_1_12_1","unstructured":"Edward J. Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang and Weizhu Chen. 2021. LoRA: Low-Rank Adaptation of Large Language Models. arxiv: 2106.09685 [cs.CL]"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_2_1_15_1","unstructured":"Yuval Kirstain Adam Polyak Uriel Singer Shahbuland Matiana Joe Penna and Omer Levy. 2023. Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation. arxiv: 2305.01569 [cs.CV]"},{"key":"e_1_3_2_1_16_1","unstructured":"Kimin Lee Hao Liu Moonkyung Ryu Olivia Watkins Yuqing Du Craig Boutilier Pieter Abbeel Mohammad Ghavamzadeh and Shixiang Shane Gu. 2023. Aligning Text-to-Image Models using Human Feedback. arxiv: 2302.12192 [cs.LG]"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01502"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01578"},{"key":"e_1_3_2_1_19_1","volume-title":"ControlNet: Improving Conditional Controls with Efficient Consistency Feedback. arXiv preprint arXiv:2404.07987","author":"Li Ming","year":"2024","unstructured":"Ming Li, Taojiannan Yang, Huafeng Kuang, Jie Wu, Zhaoning Wang, Xuefeng Xiao, and Chen Chen. 2024. ControlNet: Improving Conditional Controls with Efficient Consistency Feedback. arXiv preprint arXiv:2404.07987 (2024)."},{"key":"e_1_3_2_1_20_1","unstructured":"Haotian Liu Chunyuan Li Yuheng Li and Yong Jae Lee. 2023. Improved Baselines with Visual Instruction Tuning. arxiv: 2310.03744 [cs.CV]"},{"key":"e_1_3_2_1_21_1","volume-title":"Samaneh Azadi, Gong Zhang, Arman Chopikyan, Yuxiao Hu, Humphrey Shi, Anna Rohrbach, and Trevor Darrell.","author":"Liu Xihui","year":"2022","unstructured":"Xihui Liu, Dong Huk Park, Samaneh Azadi, Gong Zhang, Arman Chopikyan, Yuxiao Hu, Humphrey Shi, Anna Rohrbach, and Trevor Darrell. 2022. More Control for Free! Image Synthesis with Semantic Diffusion Guidance. arxiv: 2112.05744 [cs.CV]"},{"key":"e_1_3_2_1_22_1","unstructured":"Jian Ma Junhao Liang Chen Chen and Haonan Lu. 2023. Subject-Diffusion:Open Domain Personalized Text-to-Image Generation without Test-time Fine-tuning. arxiv: 2307.11410 [cs.CV]"},{"key":"e_1_3_2_1_23_1","volume-title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. arxiv: 2112.10741 [cs.CV]","author":"Nichol Alex","year":"2022","unstructured":"Alex Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, and Mark Chen. 2022. GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. arxiv: 2112.10741 [cs.CV]"},{"key":"e_1_3_2_1_25_1","unstructured":"OpenAI. 2023. Introducing chatgpt. arxiv: 2303.08774 [cs.CL]"},{"key":"e_1_3_2_1_26_1","unstructured":"Long Ouyang Jeff Wu Xu Jiang Diogo Almeida Carroll L. Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray John Schulman Jacob Hilton Fraser Kelton Luke Miller Maddie Simens Amanda Askell Peter Welinder Paul Christiano Jan Leike and Ryan Lowe. 2022. Training language models to follow instructions with human feedback. arxiv: 2203.02155 [cs.CL]"},{"key":"e_1_3_2_1_27_1","unstructured":"Junting Pan Keqiang Sun Yuying Ge Hao Li Haodong Duan Xiaoshi Wu Renrui Zhang Aojun Zhou Zipeng Qin Yi Wang Jifeng Dai Yu Qiao and Hongsheng Li. 2023. JourneyDB: A Benchmark for Generative Image Understanding. arxiv: 2307.00716 [cs.CV]"},{"key":"e_1_3_2_1_28_1","volume-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952","author":"Podell Dustin","year":"2023","unstructured":"Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas M\u00fcller, Joe Penna, and Robin Rombach. 2023. Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)."},{"key":"e_1_3_2_1_29_1","unstructured":"Aditya Ramesh Prafulla Dhariwal Alex Nichol Casey Chu and Mark Chen. 2022. Hierarchical Text-Conditional Image Generation with CLIP Latents. arxiv: 2204.06125 [cs.CV]"},{"key":"e_1_3_2_1_30_1","volume-title":"International Conference on Machine Learning. PMLR, 8821--8831","author":"Ramesh Aditya","year":"2021","unstructured":"Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. Zero-shot text-to-image generation. In International Conference on Machine Learning. PMLR, 8821--8831."},{"key":"e_1_3_2_1_31_1","volume-title":"Kandinsky: an improved text-to-image synthesis with image prior and latent diffusion. arXiv preprint arXiv:2310.03502","author":"Razzhigaev Anton","year":"2023","unstructured":"Anton Razzhigaev, Arseniy Shakhmatov, Anastasia Maltseva, Vladimir Arkhipkin, Igor Pavlov, Ilya Ryabov, Angelina Kuts, Alexander Panchenko, Andrey Kuznetsov, and Denis Dimitrov. 2023. Kandinsky: an improved text-to-image synthesis with image prior and latent diffusion. arXiv preprint arXiv:2310.03502 (2023)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Yuxi Ren Jie Wu Yanzuo Lu Huafeng Kuang Xin Xia Xionghui Wang Qianqian Wang Yixing Zhu Pan Xie Shiyin Wang et al. 2024. ByteEdit: Boost Comply and Accelerate Generative Image Editing. arXiv preprint arXiv:2404.04860 (2024).","DOI":"10.1007\/978-3-031-72646-0_11"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Robin Rombach Andreas Blattmann Dominik Lorenz Patrick Esser and Bj\u00f6rn Ommer. 2022. High-Resolution Image Synthesis with Latent Diffusion Models. arxiv: 2112.10752 [cs.CV]","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Nataniel Ruiz Yuanzhen Li Varun Jampani Yael Pritch Michael Rubinstein and Kfir Aberman. 2023. DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation. arxiv: 2208.12242 [cs.CV]","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_2_1_35_1","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, et al. 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in Neural Information Processing Systems, Vol. 35 (2022), 36479--36494.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_36_1","volume-title":"Burcu Karagol Ayan, Tim Salimans, et al.","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, et al. 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in neural information processing systems, Vol. 35 (2022), 36479--36494."},{"key":"e_1_3_2_1_37_1","unstructured":"Christoph Schuhmann Romain Beaumont Richard Vencu Cade Gordon Ross Wightman Mehdi Cherti Theo Coombes Aarush Katta Clayton Mullis Mitchell Wortsman Patrick Schramowski Srivatsa Kundurthy Katherine Crowson Ludwig Schmidt Robert Kaczmarczyk and Jenia Jitsev. 2022. LAION-5B: An open large-scale dataset for training next generation image-text models. arxiv: 2210.08402 [cs.CV] https:\/\/arxiv.org\/abs\/2210.08402"},{"key":"e_1_3_2_1_38_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"key":"e_1_3_2_1_39_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_40_1","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar Aurelien Rodriguez Armand Joulin Edouard Grave and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. arxiv: 2302.13971 [cs.CL]"},{"key":"e_1_3_2_1_41_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale Dan Bikel Lukas Blecher Cristian Canton Ferrer Moya Chen Guillem Cucurull David Esiobu Jude Fernandes Jeremy Fu Wenyin Fu Brian Fuller Cynthia Gao Vedanuj Goswami Naman Goyal Anthony Hartshorn Saghar Hosseini Rui Hou Hakan Inan Marcin Kardas Viktor Kerkez Madian Khabsa Isabel Kloumann Artem Korenev Punit Singh Koura Marie-Anne Lachaux Thibaut Lavril Jenya Lee Diana Liskovich Yinghai Lu Yuning Mao Xavier Martinet Todor Mihaylov Pushkar Mishra Igor Molybog Yixin Nie Andrew Poulton Jeremy Reizenstein Rashi Rungta Kalyan Saladi Alan Schelten Ruan Silva Eric Michael Smith Ranjan Subramanian Xiaoqing Ellen Tan Binh Tang Ross Taylor Adina Williams Jian Xiang Kuan Puxin Xu Zheng Yan Iliyan Zarov Yuchen Zhang Angela Fan Melanie Kambadur Sharan Narang Aurelien Rodriguez Robert Stojnic Sergey Edunov and Thomas Scialom. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. arxiv: 2307.09288 [cs.CL]"},{"key":"e_1_3_2_1_42_1","unstructured":"Xiaoshi Wu Yiming Hao Keqiang Sun Yixiong Chen Feng Zhu Rui Zhao and Hongsheng Li. 2023. Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis. arxiv: 2306.09341 [cs.CV]"},{"key":"e_1_3_2_1_43_1","unstructured":"Xiaoshi Wu Keqiang Sun Feng Zhu Rui Zhao and Hongsheng Li. 2023. Human Preference Score: Better Aligning Text-to-Image Models with Human Preference. arxiv: 2303.14420 [cs.CV]"},{"key":"e_1_3_2_1_44_1","unstructured":"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. arxiv: 2304.05977 [cs.CV]"},{"key":"e_1_3_2_1_45_1","volume-title":"Rrhf: Rank responses to align language models with human feedback without tears. arXiv preprint arXiv:2304.05302","author":"Yuan Zheng","year":"2023","unstructured":"Zheng Yuan, Hongyi Yuan, Chuanqi Tan, Wei Wang, Songfang Huang, and Fei Huang. 2023. Rrhf: Rank responses to align language models with human feedback without tears. arXiv preprint arXiv:2304.05302 (2023)."},{"key":"e_1_3_2_1_46_1","unstructured":"Aohan Zeng Xiao Liu Zhengxiao Du Zihan Wang Hanyu Lai Ming Ding Zhuoyi Yang Yifan Xu Wendi Zheng Xiao Xia et al. 2022. Glm-130b: An open bilingual pre-trained model. arXiv preprint arXiv:2210.02414 (2022)."},{"key":"e_1_3_2_1_47_1","volume-title":"2023 d. GSmoothFace: Generalized Smooth Talking Face Generation via Fine Grained 3D Face Guidance. arXiv preprint arXiv:2312.07385","author":"Zhang Haiming","year":"2023","unstructured":"Haiming Zhang, Zhihao Yuan, Chaoda Zheng, Xu Yan, Baoyuan Wang, Guanbin Li, Song Wu, Shuguang Cui, and Zhen Li. 2023 d. GSmoothFace: Generalized Smooth Talking Face Generation via Fine Grained 3D Face Guidance. arXiv preprint arXiv:2312.07385 (2023)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01601"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00363"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02280"},{"key":"e_1_3_2_1_51_1","unstructured":"Jiacheng Zhang Jie Wu Yuxi Ren Xin Xia Huafeng Kuang Pan Xie Jiashi Li Xuefeng Xiao Weilin Huang Min Zheng et al. 2024. UniFL: Improve Stable Diffusion via Unified Feedback Learning. arXiv preprint arXiv:2404.05595 (2024)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"crossref","unstructured":"Lvmin Zhang Anyi Rao and Maneesh Agrawala. 2023. Adding Conditional Control to Text-to-Image Diffusion Models. arxiv: 2302.05543 [cs.CV]","DOI":"10.1109\/ICCV51070.2023.00355"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680610","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680610","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:56Z","timestamp":1750295876000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680610"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":52,"alternative-id":["10.1145\/3664647.3680610","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680610","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}