Huang, L., Zhong, S.- hua, Zhang, Z., & Liu, Y. (2026). From Pixels to Logic: A Perception-Reasoning Decomposition Framework for Open-World Referring Expression Comprehension. Proceedings of the AAAI Conference on Artificial Intelligence, 40(7), 5058–5066. https://doi.org/10.1609/aaai.v40i7.37419