{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,17]],"date-time":"2026-11-17T12:18:03Z","timestamp":1794917883021,"version":"4.9.1"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:p>Agricultural landscape segmentation in the Global South is challenging as it is characterized by fragmented plots, high intra-class variance, and a scarcity of labeled training data. Recent advances in segmentation have been made by Multimodal Large Language Models (MLLMs). However, current approaches encounter critical context length bottlenecks and a domain alignment gap in understanding satellite features. We address these limitations through MAgSeg, a novel, decoder-free MLLM segmentation approach. MAgSeg is an architecturally efficient approach that enables standard MLLMs to perform segmentation of complex smallholder agricultural landscapes from high-resolution satellite imagery, without requiring auxiliary vision decoders. We introduce a novel instruction tuning data format designed to enable scalable fine-tuning and post-training on high resolution satellite imagery, which enables MAgSeg to learn from the global context of the image while generating text tokens for only a patch within the image. Extensive evaluations on datasets spanning three countries in the Global South demonstrate that MAgSeg significantly outperforms state-of-the-art MLLM baselines, offering a scalable solution to map smallholder agricultural environments.<\/jats:p>","DOI":"10.24963\/ijcai.2026\/728","type":"proceedings-article","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T22:01:13Z","timestamp":1789596073000},"page":"6546-6554","source":"Crossref","is-referenced-by-count":0,"title":["MAgSeg: Segmentation of Agricultural Landscapes in High-Resolution Satellite Imagery using Multimodal Large Language Models"],"prefix":"10.24963","author":[{"given":"Piyush","family":"Tiwary","sequence":"first","affiliation":[{"name":"Indian Institute of Science, Bangalore"},{"name":"Google DeepMind, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Utkarsh","family":"Ahuja","sequence":"additional","affiliation":[{"name":"Google LLC, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Depanshu","family":"Sani","sequence":"additional","affiliation":[{"name":"Google DeepMind, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aishwarya","family":"Jayagopal","sequence":"additional","affiliation":[{"name":"Google DeepMind, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sagar","family":"Gubbi","sequence":"additional","affiliation":[{"name":"Google DeepMind, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Subhashini","family":"Venugopalan","sequence":"additional","affiliation":[{"name":"Google Research, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alok","family":"Talekar","sequence":"additional","affiliation":[{"name":"Google DeepMind, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vaibhav","family":"Rajan","sequence":"additional","affiliation":[{"name":"Google DeepMind, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10584","event":{"name":"Thirty-Fifth International Joint Conference on Artificial Intelligence {IJCAI-26}","theme":"Artificial Intelligence","location":"Bremen, Germany","acronym":"IJCAI-2026","number":"35","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2026,8,15]]},"end":{"date-parts":[[2026,8,21]]}},"container-title":["Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2026,11,17]],"date-time":"2026-11-17T11:31:29Z","timestamp":1794915089000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2026\/728"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2026\/728","relation":{},"subject":[],"published":{"date-parts":[[2026,9]]}}}