Yuan, Z. et al. 2026. I2CD: An Invertible Causal Framework for Compositional Zero-Shot Learning via Disentangle-Compose-Disentangle. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 15 (Mar. 2026), 12295–12303. DOI:https://doi.org/10.1609/aaai.v40i15.38221.