HUANG, Weiquan et al. LLM2CLIP: Powerful Language Model Unlocks Richer Cross-Modality Representation. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 7, p. 5131–5139, 2026. DOI: 10.1609/aaai.v40i7.37427. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/37427. Acesso em: 15 may. 2026.