3 papers
cs.CL2026
SpecTr-GBV: Multi-Draft Block Verification Accelerating Speculative Decoding
Yijun Lin, Jinhao Sheng, Qingyue Cai +1
Autoregressive language models suffer from high inference latency due to their sequential decoding nature. Speculative decoding (SD) mitigates this by employing a lightweight draft…
math.AP2025
Quantization of blow-up masses for the Finsler -Liouville equation
Xia Huang, Yuan Li, Dong Ye +1
The quantization results for blow-up phenomena play crucial roles in the analysis of partial differential equations. Here we quantify the blow-up masses to the following Finsler $N…
math.AP2025
Normal conformal metrics with prescribed -Curvature in
Xia Huang, Dong Ye, Feng Zhou
We consider the -curvature equation \begin{equation}\label{0.1} (-Î)^n u = K(x)e^{2nu}\quad\text{in} ~\mathbb{R}^{2n} \ (n \geq 2) \end{equation} where is a given non const…