Wang, Wentao, Chunyang Liu, Kehua Sheng, Bo Zhang, and Yan Wang. “Semore: VLM-Guided Enhanced Semantic Motion Representations for Visual Reinforcement Learning”. Proceedings of the AAAI Conference on Artificial Intelligence 40, no. 12 (March 14, 2026): 10154–10162. Accessed May 15, 2026. https://ojs.aaai.org/index.php/AAAI/article/view/37983.