Bao, R., Wang, B., Wang, X., Li, H., Zheng, R., Rutkowski, L., … Tao, D. (2026). Time-Frequency Token Advantage Clipping for Training Efficient Large Reasoning Model. Proceedings of the AAAI Conference on Artificial Intelligence, 40(36), 30049–30057. https://doi.org/10.1609/aaai.v40i36.40253