{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:52:11Z","timestamp":1786121531251,"version":"build-2736575974"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"NSF"},{"name":"High Performance Computing Resource in the Core Facility for Advanced Research Computing with Case Western Reserve University","award":["NSF-2117439"],"award-info":[{"award-number":["NSF-2117439"]}]},{"name":"OpenAI Researcher Access","award":["0000007745"],"award-info":[{"award-number":["0000007745"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1109\/tpami.2026.3688191","type":"journal-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:49:33Z","timestamp":1777492173000},"page":"10570-10584","source":"Crossref","is-referenced-by-count":1,"title":["When \u2018Yes\u2019 Meets \u2018But\u2019: Can AI Comprehend Contradictory Humor in Comics?"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3337-2029","authenticated-orcid":false,"given":"Tuo","family":"Liang","sequence":"first","affiliation":[{"name":"Case Western Reserve University","place":["Cleveland, OH, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1737-3711","authenticated-orcid":false,"given":"Zhe","family":"Hu","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8044-2284","authenticated-orcid":false,"given":"Jing","family":"Li","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Case Western Reserve University","place":["Cleveland, OH, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5411-0411","authenticated-orcid":false,"given":"Yiren","family":"Lu","sequence":"additional","affiliation":[{"name":"Case Western Reserve University","place":["Cleveland, OH, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunlai","family":"Zhou","sequence":"additional","affiliation":[{"name":"Case Western Reserve University","place":["Cleveland, OH, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7777-7356","authenticated-orcid":false,"given":"Yiran","family":"Qiao","sequence":"additional","affiliation":[{"name":"Case Western Reserve University","place":["Cleveland, OH, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5034-1407","authenticated-orcid":false,"given":"Disheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Case Western Reserve University","place":["Cleveland, OH, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jierui","family":"Peng","sequence":"additional","affiliation":[{"name":"Case Western Reserve University","place":["Cleveland, OH, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4237-6607","authenticated-orcid":false,"given":"Jing","family":"Ma","sequence":"additional","affiliation":[{"name":"Case Western Reserve University","place":["Cleveland, OH, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9588-5854","authenticated-orcid":false,"given":"Yu","family":"Yin","sequence":"additional","affiliation":[{"name":"Case Western Reserve University","place":["Cleveland, OH, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Language models, agent models, and world models: The law for machine reasoning and planning","author":"Hu","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.41"},{"key":"ref3","article-title":"Artificial general intelligence: Roadmap to achieving human-level capabilities","volume":"10","author":"Rayhan","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-40858-3"},{"key":"ref5","volume-title":"The Power of Comics: History, Form and Culture","author":"Duncan","year":"2009"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.113"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.4324\/9780203427798"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.14325\/mississippi\/9781617037702.001.0001"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1046\/j.0034-0472.2003.03703002.x"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1111\/j.1475-5661.2009.00376.x"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1017\/S1755020311000219"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/1468794120918845"},{"key":"ref13","article-title":"Eliminating reasoning via inferring with planning: A new framework to guide LLMs\u2019 non-linear thinking","author":"Tong","year":"2023"},{"key":"ref14","article-title":"Sparks of artificial general intelligence: Early experiments with GPT-4","author":"Bubeck","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1494"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref17","article-title":"Llama 3 model card","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1308"},{"key":"ref20","article-title":"Spatial intelligence in vision-language models: A comprehensive survey","author":"Liu","year":"2026","journal-title":"Res. Square"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00247"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"ref23","article-title":"NEBULA: Do we evaluate vision-language-action agents correctly?","author":"Peng","year":"2025"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.567"},{"key":"ref25","article-title":"Exploring the spectrum of visio-linguistic compositionality and recognition","author":"Oh","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW69685.2025.00168"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.137"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01856"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3778357"},{"key":"ref30","first-page":"1849","article-title":"Recognizing humour using word associations and humour anchor extraction","volume-title":"Proc. 27th Int. Conf. Comput. Linguistics","author":"Cattle","year":"2018"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1284"},{"key":"ref32","first-page":"29","article-title":"A survey on approaches to computational humor generation","volume-title":"Proc. 4th Joint SIGHUM Workshop Comput. Linguistics Cultural Heritage, Social Sci., Humanities Literature","author":"Amin","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.wassa-1.29"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01258"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783388"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00064"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.498"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00212"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3652583.3658094"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.89"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.63317\/5k45wd8e9eqd"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.342"},{"key":"ref43","article-title":"See, think, confirm: Interactive prompting between vision and language models for knowledge-based visual reasoning","author":"Chen","year":"2023"},{"key":"ref44","first-page":"132","article-title":"HYDRA: A hyper agent for dynamic compositional visual reasoning","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Ke","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"ref46","article-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref47","article-title":"CogVLM2: Visual language models for image and video understanding","author":"Hong","year":"2024"},{"key":"ref48","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref49","article-title":"Llava-next: Improved reasoning, OCR, and world knowledge","author":"Liu","year":"2024"},{"key":"ref50","article-title":"Gemini in reasoning: Unveiling commonsense in multimodal large language models","author":"Wang","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00517"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0182"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.763"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148215"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0906"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref57","article-title":"LLaVa-OneVision: Easy visual task transfer","author":"Li","year":"2025","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref58","article-title":"GPT-4o system card","author":"Hurst","year":"2024"},{"key":"ref59","first-page":"18 378","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","year":"2023"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09422-z"},{"key":"ref61","article-title":"Qwen2. 5 technical report","author":"Yang","year":"2024"},{"key":"ref62","article-title":"Evaluation of text generation: A survey","author":"Celikyilmaz","year":"2020"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00561"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/34\/11643729\/11498593-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11643729\/11498593.pdf?arnumber=11498593","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T04:59:19Z","timestamp":1786078759000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11498593\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":64,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3688191","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]}}}