[1]
Li, Q. et al. 2026. AdaFuse: Accelerating Dynamic Adapter Inference via Token-Level Pre-Gating and Fused Kernel Optimization. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 37 (Mar. 2026), 31680–31688. DOI:https://doi.org/10.1609/aaai.v40i37.40435.