{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:21:52Z","timestamp":1777890112987,"version":"3.51.4"},"reference-count":74,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00323","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"3378-3389","source":"Crossref","is-referenced-by-count":0,"title":["DWIM: Towards Tool-Aware Visual Reasoning via Discrepancy-Aware Workflow Generation & Instruct-Masking Tuning"],"prefix":"10.1109","author":[{"given":"Fucai","family":"Ke","sequence":"first","affiliation":[{"name":"Building 4.0 CR"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vijay","family":"Kumar B G","sequence":"additional","affiliation":[{"name":"NEC Labs America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingjian","family":"Leng","sequence":"additional","affiliation":[{"name":"ANU"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhixi","family":"Cai","sequence":"additional","affiliation":[{"name":"Monash University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zaid","family":"Khan","sequence":"additional","affiliation":[{"name":"UNC Chapel Hill"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiqing","family":"Wang","sequence":"additional","affiliation":[{"name":"Monash University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pari Delir","family":"Haghighi","sequence":"additional","affiliation":[{"name":"Monash University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hamid","family":"Rezatofighi","sequence":"additional","affiliation":[{"name":"Monash University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manmohan","family":"Chandraker","sequence":"additional","affiliation":[{"name":"NEC Labs America"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018076"},{"key":"ref2","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref3","first-page":"279","article-title":"Neuro-symbolic visual reasoning: Disentangling","volume-title":"International Conference on Machine Learning","author":"Amizadeh"},{"key":"ref4","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref5","first-page":"1877","volume":"33","author":"Brown","year":"2020","journal-title":"Language models are few-shot learners. Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2025.3592098"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02232"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"issue":"240","key":"ref9","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00101"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00106"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref13","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref14","volume-title":"Multi-modal agent tuning: Building a vlm-driven agent for efficient tool usage","author":"Gao","year":"2025"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaa8685"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1355"},{"key":"ref18","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00916"},{"key":"ref20","first-page":"9118","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","volume-title":"International Conference on Machine Learning","author":"Huang"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref22","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref23","article-title":"Mistral 7b","author":"Jiang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02578"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.111300"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_8"},{"key":"ref28","first-page":"2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of naacL-HLT","author":"Devlin"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2472"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01360"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1613"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.483"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref34","first-page":"17044","article-title":"Naturalbench: Evaluating vision-language models on natural adversarial samples","volume":"37","author":"Li","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref35","first-page":"1973019742","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref38","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref40","volume-title":"Introducing Llama. 3.1: Our most capable models to date. Meta","year":"2024"},{"key":"ref41","article-title":"Chameleon: Plug-and-play compositional reasoning with large language models","volume":"36","author":"Lu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref42","article-title":"Gerea: Question-aware prompt captions for knowledge-based visual question answering","author":"Ma","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01764"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01367"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2011"},{"key":"ref47","article-title":"Agent planning with world knowledge model","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Qiao"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.165"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3704435"},{"key":"ref50","volume-title":"Qwen2.5 technical report","author":"Qwen","year":"2025"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"ref52","article-title":"Hugginggpt: Solving ai tasks with chatgpt and its friends in hugging face","volume":"36","author":"Shen","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0377"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00517"},{"key":"ref56","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref57","article-title":"Voyager: An open-ended embodied agent with large language models","author":"Wang","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref58","first-page":"5020850232","article-title":"Executable code actions elicit better LLM agents","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Wang"},{"key":"ref59","first-page":"5117751191","article-title":"Trove: inducing verifiable and efficient toolboxes for solving programmatic tasks","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Zhiruo Wang"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-503"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0817"},{"key":"ref62","article-title":"Stateflow: Enhancing llm task-solving through state-driven workflows","volume-title":"First Conference on Language Modeling","author":"Wu"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.93"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02482"},{"key":"ref65","article-title":"React: Synergizing reasoning and acting in language models","author":"Yao","year":"2022","journal-title":"ICLR"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.670"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.755"},{"key":"ref68","article-title":"Craft: Customizing llms by creating and retrieving from specialized toolsets","volume-title":"The Twelfth International Conference on Learning Representations","author":"Yuan"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3604237.3626908"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3522"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413761"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29936"},{"key":"ref73","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhu"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.205"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444178.pdf?arnumber=11444178","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:29:10Z","timestamp":1777613350000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444178\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00323","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}