TANG, Canhui et al. TSPO: Temporal Sampling Policy Optimization for Long-form Video Language Understanding. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 11, p. 9368–9376, 2026. DOI: 10.1609/aaai.v40i11.37896. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/37896. Acesso em: 11 may. 2026.