{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:26:06Z","timestamp":1773800766980,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Multimodal table understanding, which aims for a comprehensive grasp of table content by integrating cellular text, tabular structure, and visual presentation, remains a core yet challenging area of research.\nWe identify that the structural complexity of a table, quantifiable by intrinsic properties such as the ratio of merged cells and the total number of cells, presents a significant obstacle for existing models. \nOur empirical analysis reveals that the performance of leading Multimodal Large Language Models (MLLMs) deteriorates markedly as table complexity increases, exposing a critical vulnerability in their ability to perceive and reason over intricate tabular data.\nTo address this challenge, we propose MM-Table-R1, a model enhanced through difficulty-aware reinforcement learning (RL) post-training strategy. \nSpecifically, we introduce both task-level and data-level curriculum learning. \nThe task-level curriculum is designed to establish a capability ladder, where the model first learns basic perceptual and semantic alignment of table data, and then progresses to acquiring multi-step reasoning capabilities.\nThe data-level curriculum ensures that the model is not exposed to difficult samples prematurely, facilitating a more gradual and effective learning process.\nFurthermore, we invest considerable effort in constructing a high-quality, large-scale training corpus by curating and processing data from diverse open-source table datasets, ensuring that each instance is paired with an objectively verifiable reward signal.\nDemonstrating exceptional parameter efficiency, our 3B-parameter model sets a new benchmark by surpassing both established 3B and 7B models, including those specifically designed for table reasoning.<\/jats:p>","DOI":"10.1609\/aaai.v40i1.37042","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T22:42:38Z","timestamp":1773787358000},"page":"755-763","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal Table Understanding with Difficulty-aware Reinforcement Learning"],"prefix":"10.1609","volume":"40","author":[{"given":"Chaohu","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyu","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"YongXiang","family":"Hua","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linli","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/37042\/41004","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/37042\/41004","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T22:42:38Z","timestamp":1773787358000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/37042"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i1.37042","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}