[1]
Ou, Z. et al. 2026. ParaDySe: A Parallel Strategy Switching Framework for Dynamic Sequences in Transformer-based Large Language Models. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 29 (Mar. 2026), 24648–24655. DOI:https://doi.org/10.1609/aaai.v40i29.39649.