FlashSinkhorn: IO-Aware Entropic Optimal Transport on GPUFelix YeXingjie Liet al.2026ICML 2026Conference paper
DropKV: Decoupling Residual-Output Perturbation for Near-Optimal KV-Cache EvictionAozhong ZhangSelcuk Gurseset al.2026ICML 2026Workshop paper