{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T11:35:27Z","timestamp":1793964927642,"version":"4.8.0"},"reference-count":81,"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\/iccv51701.2025.00863","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"9241-9251","source":"Crossref","is-referenced-by-count":10,"title":["Perspective-Aware Reasoning in Vision-Language Models via Mental Imagery Simulation"],"prefix":"10.1109","author":[{"given":"Phillip Y.","family":"Lee","sequence":"first","affiliation":[{"name":"KAIST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jihyeon","family":"Je","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chanho","family":"Park","sequence":"additional","affiliation":[{"name":"KAIST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leonidas","family":"Guibas","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mikaela Angelina","family":"Uy","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minhyuk","family":"Sung","sequence":"additional","affiliation":[{"name":"KAIST"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","article-title":"Qwen2.5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109209"},{"key":"ref4","article-title":"Depth pro: Sharp monocular metric depth in less than a second","volume-title":"ICLR","author":"Bochkovskii","year":"2025"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2006.10.005"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128671"},{"key":"ref7","article-title":"End-toend object detection with transformers","volume-title":"ECCV","author":"Carion","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27888"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4293"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1037\/10096-006"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.concog.2022.103352"},{"key":"ref13","volume-title":"Blender - a 3d modelling and rendering package","year":"2018"},{"key":"ref14","article-title":"Molmo and pixmo: Open weights and open data for state-of-the-art multimodal models","author":"Deitke","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9280.1997.tb00442.x"},{"key":"ref16","article-title":"Minedojo: Building open-ended embodied agents with internet-scale knowledge","author":"Fan","year":"2022","journal-title":"NeurIPS"},{"key":"ref17","article-title":"RA Finke","volume-title":"Principles of mental imagery","year":"1989"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73337-6_9"},{"key":"ref19","article-title":"Seeing through their eyes: Evaluating visual perspective taking in vision language models","author":"G\u00f3ral","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00371"},{"key":"ref22","article-title":"Visual sketchpad: Sketching as a visual chain of thought for multimodal language models","author":"Hu","year":"2024","journal-title":"NeurIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00916"},{"key":"ref24","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01660"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.568"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1037\/0096-1523.4.1.47"},{"key":"ref30","article-title":"Scaffolding coordinates to promote vision-language coordination in large multi-modal models","author":"Lei","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.106"},{"key":"ref33","article-title":"Imagine while reasoning in space: Multimodal visualization-ofthought","author":"Li","year":"2025","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"ICML","author":"Li","year":"2022"},{"key":"ref35","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"ICML","author":"Li","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref37","article-title":"The 3d-pc: a benchmark for visual perspective taking in humans and machines","volume-title":"ICLR","author":"Linsley","year":"2025"},{"key":"ref38","article-title":"Coarse correspondence elicit 3d spacetime understanding in multimodal language model","volume-title":"CVPR","author":"Liu","year":"2025"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00566"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref41","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00960"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref44","article-title":"Spatialcot: Advancing spatial reasoning through coordinate alignment and chain-of-thought for embodied task planning","author":"Liu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Spatialpin: Enhancing spatial reasoning capabilities of vision-language models through prompting and interacting 3d priors","author":"Ma","year":"2024","journal-title":"NeurIPS"},{"key":"ref46","article-title":"3dsrbench: A comprehensive 3d spatial reasoning benchmark","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01811"},{"key":"ref48","article-title":"Mental imagery","author":"Nanay","year":"2021","journal-title":"The Stanford Encyclopedia of Philosophy"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.4324\/9781315798868"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0917-8_17"},{"key":"ref51","author":"Ramakrishnan","year":"2025","journal-title":"Does spatial cognition emerge in frontier models? In ICLR"},{"key":"ref52","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv"},{"key":"ref53","article-title":"Sat: Spatial aptitude training for multimodal language models","author":"Ray","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"Visual chain of thought: bridging logical gaps with multimodal infillings","author":"Rose","year":"2023","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1177\/17470218211054474"},{"key":"ref56","article-title":"Visual cot: Advancing multi-modal language models with a comprehensive dataset and benchmark for chain-of-thought reasoning","author":"Shao","year":"2024","journal-title":"NeurIPS"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1126\/science.171.3972.701"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1195"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01101"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01470"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"ref62","article-title":"Sparkle: Mastering basic spatial capabilities in vision language models elicits generalization to composite spatial reasoning","author":"Tang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref63","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref64","article-title":"Cambrian-1: A fully open, vision-centric exploration of multimodal 11 ms","author":"Tong","year":"2024","journal-title":"NeurIPS"},{"key":"ref65","article-title":"Is a picture worth a thousand words? delving into spatial reasoning for vision language models","author":"Wang","year":"2024","journal-title":"NeurIPS"},{"key":"ref66","article-title":"Orient anything: Learning robust object orientation estimation from rendering 3d models","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref67","article-title":"Visual prompting in multimodal large language models: A survey","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref68","article-title":"Mind\u2019s eye of 11 ms: Visualization-of-thought elicits spatial reasoning in large language models","author":"Wu","year":"2024","journal-title":"NeurIPS"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_10"},{"key":"ref70","article-title":"How2comm: Communication-efficient and collaboration-pragmatic multiagent perception","author":"Yang","year":"2023","journal-title":"NeurIPS"},{"key":"ref71","article-title":"Set-of-mark prompting unleashes extraordinary visual grounding in gpt-4v","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00994"},{"key":"ref73","article-title":"Fine-grained visual prompting","author":"Yang","year":"2023","journal-title":"NeurIPS"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128705"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3613256"},{"key":"ref76","article-title":"Robopoint: A vision-language model for spatial affordance prediction for robotics","volume-title":"CORL","author":"Yuan","year":"2024"},{"key":"ref77","article-title":"Sphere: A hierarchical evaluation on spatial perception and reasoning for visionlanguage models","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref78","article-title":"Do visionlanguage models represent space and how? evaluating spatial frame of reference under ambiguities","volume-title":"ICLR","author":"Zhang","year":"2025"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00166"},{"key":"ref80","article-title":"Image-of-thought prompting for visual reasoning refinement in multimodal large language models","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref81","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","volume-title":"ICLR","author":"Zhu","year":"2021"}],"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\/11444176.pdf?arnumber=11444176","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:45:22Z","timestamp":1777531522000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444176\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":81,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00863","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}