{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:26:10Z","timestamp":1777656370710,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":40,"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"}],"funder":[{"name":"NSFC","award":["No. 62272411"],"award-info":[{"award-number":["No. 62272411"]}]},{"name":"Key Research and Development Projects in Zhejiang Province","award":["No. 2024C01106"],"award-info":[{"award-number":["No. 2024C01106"]}]},{"name":"Research funding from FinVolution Group"},{"name":"National Key Research and Development Project of China","award":["2022ZD0160101"],"award-info":[{"award-number":["2022ZD0160101"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681082","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"7649-7657","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["De-fine:\n            <u>De<\/u>\n            composing and Re\n            <u>fin<\/u>\n            ing Visual Programs with Auto-Feedback"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9705-5398","authenticated-orcid":false,"given":"Minghe","family":"Gao","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2258-1291","authenticated-orcid":false,"given":"Juncheng","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3026-6347","authenticated-orcid":false,"given":"Hao","family":"Fei","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1161-8546","authenticated-orcid":false,"given":"Liang","family":"Pang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8106-9768","authenticated-orcid":false,"given":"Wei","family":"Ji","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3131-6916","authenticated-orcid":false,"given":"Guoming","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6529-8088","authenticated-orcid":false,"given":"Zheqi","family":"Lv","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5988-7609","authenticated-orcid":false,"given":"Wenqiao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7356-9711","authenticated-orcid":false,"given":"Siliang","family":"Tang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9017-2508","authenticated-orcid":false,"given":"Yueting","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"TallyQA: Answering Complex Counting Questions. arXiv preprint arXiv:1810.12440","author":"Acharya Manoj","year":"2018","unstructured":"Manoj Acharya, Kushal Kafle, and Christopher Kanan. 2018. TallyQA: Answering Complex Counting Questions. arXiv preprint arXiv:1810.12440 (2018)."},{"key":"e_1_3_2_1_2_1","volume-title":"Oh (Eds.)","volume":"35","author":"Alayrac Jean-Baptiste","year":"2022","unstructured":"Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katherine Millican, Malcolm Reynolds, Roman Ring, Eliza Rutherford, Serkan Cabi, Tengda Han, Zhitao Gong, Sina Samangooei, Marianne Monteiro, Jacob L Menick, Sebastian Borgeaud, Andy Brock, Aida Nematzadeh, Sahand Sharifzadeh, Ricardo Barreira, Oriol Vinyals, Andrew Zisserman, and Kar\u00e9n Simonyan. 2022. Flamingo: a Visual Language Model for Few-Shot Learning. In Advances in Neural Information Processing Systems, S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (Eds.), Vol. 35. Curran Associates, Inc., 23716--23736. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/ 960a172bc7fbf0177ccccbb411a7d800-Paper-Conference.pdf"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_1_5_1","volume-title":"Teaching large language models to self-debug. arXiv preprint arXiv:2304.05128","author":"Chen Xinyun","year":"2023","unstructured":"Xinyun Chen, Maxwell Lin, Nathanael Sch\u00e4rli, and Denny Zhou. 2023. Teaching large language models to self-debug. arXiv preprint arXiv:2304.05128 (2023)."},{"key":"e_1_3_2_1_6_1","volume-title":"GENOME: GenerativE Neuro-symbOlic visual reasoning by growing and reusing ModulEs. arXiv:2311.04901 [cs.CV]","author":"Chen Zhenfang","year":"2023","unstructured":"Zhenfang Chen, Rui Sun, Wenjun Liu, Yining Hong, and Chuang Gan. 2023. GENOME: GenerativE Neuro-symbOlic visual reasoning by growing and reusing ModulEs. arXiv:2311.04901 [cs.CV]"},{"key":"e_1_3_2_1_7_1","volume-title":"Corey Lynch, Aakanksha Chowdhery, Brian Ichter, Ayzaan Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, et al.","author":"Driess Danny","year":"2023","unstructured":"Danny Driess, Fei Xia, Mehdi SM Sajjadi, Corey Lynch, Aakanksha Chowdhery, Brian Ichter, Ayzaan Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, et al. 2023. Palm-e: An embodied multimodal language model. arXiv preprint arXiv:2303.03378 (2023)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"e_1_3_2_1_9_1","volume-title":"Georg Von Krogh, and Sebastian Spaeth","author":"Haefliger Stefan","year":"2008","unstructured":"Stefan Haefliger, Georg Von Krogh, and Sebastian Spaeth. 2008. Code reuse in open source software. Management science 54, 1 (2008), 180--193."},{"key":"e_1_3_2_1_10_1","volume-title":"A retrieve-and-edit framework for predicting structured outputs. Advances in Neural Information Processing Systems 31","author":"Hashimoto Tatsunori B","year":"2018","unstructured":"Tatsunori B Hashimoto, Kelvin Guu, Yonatan Oren, and Percy S Liang. 2018. A retrieve-and-edit framework for predicting structured outputs. Advances in Neural Information Processing Systems 31 (2018)."},{"key":"e_1_3_2_1_11_1","volume-title":"Retrieval-based neural code generation. arXiv preprint arXiv:1808.10025","author":"Hayati Shirley Anugrah","year":"2018","unstructured":"Shirley Anugrah Hayati, Raphael Olivier, Pravalika Avvaru, Pengcheng Yin, Anthony Tomasic, and Graham Neubig. 2018. Retrieval-based neural code generation. arXiv preprint arXiv:1808.10025 (2018)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.325"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"e_1_3_2_1_15_1","volume-title":"Decomposed prompting: A modular approach for solving complex tasks. arXiv preprint arXiv:2210.02406","author":"Khot Tushar","year":"2022","unstructured":"Tushar Khot, Harsh Trivedi, Matthew Finlayson, Yao Fu, Kyle Richardson, Peter Clark, and Ashish Sabharwal. 2022. Decomposed prompting: A modular approach for solving complex tasks. arXiv preprint arXiv:2210.02406 (2022)."},{"key":"e_1_3_2_1_16_1","volume-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)."},{"key":"e_1_3_2_1_17_1","volume-title":"Skcoder: A sketch-based approach for automatic code generation. arXiv preprint arXiv:2302.06144","author":"Li Jia","year":"2023","unstructured":"Jia Li, Yongmin Li, Ge Li, Zhi Jin, Yiyang Hao, and Xing Hu. 2023. Skcoder: A sketch-based approach for automatic code generation. arXiv preprint arXiv:2302.06144 (2023)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Yujia Li David Choi Junyoung Chung Nate Kushman Julian Schrittwieser R\u00e9mi Leblond Tom Eccles James Keeling Felix Gimeno Agustin Dal Lago Thomas Hubert Peter Choy Cyprien de Masson d'Autume Igor Babuschkin Xinyun Chen Po-Sen Huang Johannes Welbl Sven Gowal Alexey Cherepanov James Molloy Daniel J. Mankowitz Esme Sutherland Robson Pushmeet Kohli Nando de Freitas Koray Kavukcuoglu and Oriol Vinyals. 2022. Competition-level code generation with AlphaCode. Science 378 6624 (2022) 1092--1097. https:\/\/doi.org\/10.1126\/ science.abq1158 arXiv:https:\/\/www.science.org\/doi\/pdf\/10.1126\/science.abq1158","DOI":"10.1126\/science.abq1158"},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings, Part V 13","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_21_1","unstructured":"Haotian Liu Chunyuan Li QingyangWu and Yong Jae Lee. 2023. Visual Instruction Tuning. arXiv:2304.08485 [cs.CV]"},{"key":"e_1_3_2_1_22_1","volume-title":"Self-refine: Iterative refinement with self-feedback. arXiv preprint arXiv:2303.17651","author":"Madaan Aman","year":"2023","unstructured":"Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, et al. 2023. Self-refine: Iterative refinement with self-feedback. arXiv preprint arXiv:2303.17651 (2023)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/FLOSS.2007.10"},{"key":"e_1_3_2_1_25_1","unstructured":"OpenAI. [n. d.]. GhatGPT. https:\/\/openai.com\/chatgpt."},{"key":"e_1_3_2_1_27_1","first-page":"27730","article-title":"2022. Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang Long","year":"2022","unstructured":"Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems 35 (2022), 27730--27744.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_28_1","volume-title":"Neuro-symbolic program synthesis. arXiv preprint arXiv:1611.01855","author":"Parisotto Emilio","year":"2016","unstructured":"Emilio Parisotto, Abdel-rahman Mohamed, Rishabh Singh, Lihong Li, Dengyong Zhou, and Pushmeet Kohli. 2016. Neuro-symbolic program synthesis. arXiv preprint arXiv:1611.01855 (2016)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"e_1_3_2_1_30_1","volume-title":"Reclip: A strong zero-shot baseline for referring expression comprehension. arXiv preprint arXiv:2204.05991","author":"Subramanian Sanjay","year":"2022","unstructured":"Sanjay Subramanian, William Merrill, Trevor Darrell, Matt Gardner, Sameer Singh, and Anna Rohrbach. 2022. Reclip: A strong zero-shot baseline for referring expression comprehension. arXiv preprint arXiv:2204.05991 (2022)."},{"key":"e_1_3_2_1_31_1","volume-title":"A corpus for reasoning about natural language grounded in photographs. arXiv preprint arXiv:1811.00491","author":"Suhr Alane","year":"2018","unstructured":"Alane Suhr, Stephanie Zhou, Ally Zhang, Iris Zhang, Huajun Bai, and Yoav Artzi. 2018. A corpus for reasoning about natural language grounded in photographs. arXiv preprint arXiv:1811.00491 (2018)."},{"key":"e_1_3_2_1_32_1","volume-title":"Vipergpt: Visual inference via python execution for reasoning. arXiv preprint arXiv:2303.08128","author":"Sur\u00eds D\u00eddac","year":"2023","unstructured":"D\u00eddac Sur\u00eds, Sachit Menon, and Carl Vondrick. 2023. Vipergpt: Visual inference via python execution for reasoning. arXiv preprint arXiv:2303.08128 (2023)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3417058"},{"key":"e_1_3_2_1_34_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_35_1","volume-title":"Saksham Singhal, Subhojit Som, et al.","author":"Wang Wenhui","year":"2022","unstructured":"Wenhui Wang, Hangbo Bao, Li Dong, Johan Bjorck, Zhiliang Peng, Qiang Liu, Kriti Aggarwal, Owais Khan Mohammed, Saksham Singhal, Subhojit Som, et al. 2022. Image as a foreign language: Beit pretraining for all vision and visionlanguage tasks. arXiv preprint arXiv:2208.10442 (2022)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_27"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20215"},{"key":"e_1_3_2_1_39_1","unstructured":"Qinghao Ye Haiyang Xu Guohai Xu Jiabo Ye Ming Yan Yiyang Zhou Junyang Wang Anwen Hu Pengcheng Shi Yaya Shi et al. 2023. mplug-owl: Modularization empowers large language models with multimodality. arXiv preprint arXiv:2304.14178 (2023)."},{"key":"e_1_3_2_1_40_1","unstructured":"Andy Zeng Maria Attarian Brian Ichter Krzysztof Choromanski Adrian Wong StefanWelker Federico Tombari Aveek Purohit Michael Ryoo Vikas Sindhwani et al. 2022. Socratic models: Composing zero-shot multimodal reasoning with language. arXiv preprint arXiv:2204.00598 (2022)."},{"key":"e_1_3_2_1_41_1","volume-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592","author":"Zhu Deyao","year":"2023","unstructured":"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 (2023)."}],"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\/3664647.3681082","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681082","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:52Z","timestamp":1750294672000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681082"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":40,"alternative-id":["10.1145\/3664647.3681082","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681082","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"}}]}}