{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:09:24Z","timestamp":1765339764010,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":6,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3760212","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:51Z","timestamp":1761377211000},"page":"14342-14343","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Reasoning and Planning for Multimodal Large Language Models: A Multilingual and Cross-Domain Exploration"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6608-0400","authenticated-orcid":false,"given":"Sarmistha","family":"Das","sequence":"first","affiliation":[{"name":"Indian Institute of Technology Patna, Patna, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9353-7258","authenticated-orcid":false,"given":"Akash","family":"Ghosh","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Patna, Patna, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5458-9381","authenticated-orcid":false,"given":"Sriparna","family":"Saha","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Patna, Patna, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0428-160X","authenticated-orcid":false,"given":"Koustava","family":"Goswami","sequence":"additional","affiliation":[{"name":"Adobe Research, San Jose, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1168-1609","authenticated-orcid":false,"given":"Joseph","family":"K.J","sequence":"additional","affiliation":[{"name":"Adobe Research, Bangalore, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Jean-Baptiste Alayrac Jeff Donahue Pauline Luc Antoine Miech Iain Barr Yana Hasson Karel Lenc Arthur Mensch Katherine Millican Malcolm Reynolds et al. 2022. Flamingo: a visual language model for few-shot learning. Advances in neural information processing systems Vol. 35 (2022) 23716-23736."},{"key":"e_1_3_2_1_2_1","unstructured":"D. Driess et al. 2023. PaLM-E: An Embodied Multimodal Language Model. arXiv preprint (2023). arXiv:2303.03378 [cs.AI] https:\/\/arxiv.org\/abs\/2303.03378"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01046"},{"key":"e_1_3_2_1_4_1","unstructured":"K. Singhal et al. 2022. Large Language Models Encode Clinical Knowledge. arXiv preprint (2022). arXiv:2212.13138 [cs.AI] https:\/\/arxiv.org\/abs\/2212.13138"},{"key":"e_1_3_2_1_5_1","unstructured":"Y. Wang et al. 2024. Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning. arXiv preprint (2024). arXiv:2401.06805 [cs.AI] https:\/\/arxiv.org\/abs\/2401.06805"},{"key":"e_1_3_2_1_6_1","volume-title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning. arXiv preprint","author":"Y. Yan","year":"2025","unstructured":"Y. Yan et al., 2025. Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning. arXiv preprint (2025). arXiv:2502.02871 [cs.AI] https:\/\/arxiv.org\/abs\/2502.02871"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3760212","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:05:06Z","timestamp":1765339506000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3760212"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":6,"alternative-id":["10.1145\/3746027.3760212","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3760212","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}