Hou, Guiyang, Yihui Fu, Chen Wu, Xiang Huang, Zhe Zheng, Wenqi Zhang, Yongliang Shen, and Weiming Lu. “Reality Vs Counterfactual: Multi-World Contrastive Reinforcement Learning for Enhancing MLLM’s Theory of Mind in Egocentric Videos”. Proceedings of the AAAI Conference on Artificial Intelligence 40, no. 3 (March 14, 2026): 1828-1836. Accessed May 4, 2026. https://ojs.aaai.org/index.php/AAAI/article/view/37162.