Li Q, Kong R, Li Y, Cai H, Wang S, Kong L, et al. AdaFuse: Accelerating Dynamic Adapter Inference via Token-Level Pre-Gating and Fused Kernel Optimization. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 31];40(37):31680-8. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/40435