[1]
Huang, L. et al. 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 (Mar. 2026), 5058–5066. DOI:https://doi.org/10.1609/aaai.v40i7.37419.