{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:06:28Z","timestamp":1777889188398,"version":"3.51.4"},"reference-count":49,"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"}],"funder":[{"DOI":"10.13039\/100007631","name":"CIFAR","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007631","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00687","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"7318-7328","source":"Crossref","is-referenced-by-count":0,"title":["Physics Context Builders: A Modular Framework for Physical Reasoning in Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Vahid","family":"Balazadeh","sequence":"first","affiliation":[{"name":"University of Toronto"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammadmehdi","family":"Ataei","sequence":"additional","affiliation":[{"name":"Autodesk Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyunmin","family":"Cheong","sequence":"additional","affiliation":[{"name":"Autodesk Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amir Hosein","family":"Khasahmadi","sequence":"additional","affiliation":[{"name":"Autodesk Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rahul G.","family":"Krishnan","sequence":"additional","affiliation":[{"name":"University of Toronto"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","first-page":"89","volume-title":"Infants\u2019 physical world. Current directions in psychological science","volume":"13","author":"Baillargeon","year":"2004"},{"key":"ref4","article-title":"Interaction networks for learning about objects, relations and physics","volume":"29","author":"Battaglia","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1306572110"},{"key":"ref6","article-title":"Paligemma: A versatile 3B VLM for transfer","author":"Beyer","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"GitHub - openai\/swarm: Educational framework exploring ergonomic, lightweight multi-agent orchestration","author":"Bigio","year":"2024","journal-title":"Managed by OpenAI Solution team."},{"key":"ref8","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref9","article-title":"Grounding physical concepts of objects and events through dynamic visual reasoning","volume-title":"International Conference on Learning Representations (ICLR)","author":"Chen","year":"2021"},{"key":"ref10","article-title":"Physbench: Benchmarking and enhancing vision-language models for physical world understanding","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Chow","year":"2025"},{"key":"ref11","first-page":"9112","article-title":"Attention over learned object embeddings enables complex visual reasoning","volume":"34","author":"Ding","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref12","first-page":"887","article-title":"Dynamic visual reasoning by learning differentiable physics models from video and language","volume":"34","author":"Ding","year":"2021","journal-title":"Advances In Neural Information Processing Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_24"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaaiss.v3i1.31189"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_43"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01149"},{"key":"ref17","article-title":"Phygrasp: generalizing robotic grasping with physicsinformed large multimodal models","author":"Guo","year":"2024","journal-title":"arXiv preprint"},{"issue":"2","key":"ref18","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref19","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00656"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2017.06.002"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X16001837"},{"key":"ref24","first-page":"430438","article-title":"Learning physical intuition of block towers by example","volume-title":"International conference on machine learning","author":"Lerer"},{"key":"ref25","first-page":"19730","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","year":"2023"},{"key":"ref26","article-title":"Multimodal causal reasoning benchmark: Challenging vision large language models to infer causal links between siamese images","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref28","article-title":"Moka: Open-vocabulary robotic manipulation through mark-based visual prompting","volume-title":"First Workshop on Vision-Language Models for Navigation and Manipulation at ICRA 2024","author":"Liu","year":"2024"},{"key":"ref29","article-title":"Mind\u2019s eye: Grounded language model reasoning through simulation","volume-title":"The Eleventh International Conference on Learning Representations","author":"Liu","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1037\/0278-7393.9.4.636"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10650020"},{"key":"ref32","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0917-8_17"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref35","article-title":"Beyond the imitation game: Quantifying and extrapolating the capabilities of language models","volume-title":"Transactions on machine learning research","author":"Srivastava","year":"2023"},{"key":"ref36","article-title":"Probing mechanical reasoning in large vision language models","volume-title":"ICLR 2025 Workshop on Bidirectional Human-AI Alignment","author":"Sun","year":"2025"},{"key":"ref37","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1126\/science.1196404"},{"key":"ref39","article-title":"NL-eye: Abductive NLI for images","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Ventura","year":"2025"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.652"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref42","article-title":"Galileo: Perceiving physical object properties by integrating a physics engine with deep learning","volume":"28","author":"Wu","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref43","article-title":"Learning to see physics via visual de-animation","volume":"30","author":"Wu","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref45","article-title":"Clevrer: Collision events for video representation and reasoning","volume-title":"International Conference on Learning Representations","author":"Yi","year":"2020"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref47","article-title":"Multimodal chain-ofthought reasoning in language models","author":"Zhang","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref48","first-page":"61526","article-title":"Contphy: Continuum physical concept learning and reasoning from videos","volume-title":"International Conference on Machine Learning","author":"Zheng","year":"2024"},{"key":"ref49","article-title":"Maps: Advancing multi-modal reasoning in expert-level physical science","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Zhu","year":"2025"}],"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\/11444452.pdf?arnumber=11444452","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:09:37Z","timestamp":1777612177000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444452\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00687","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}