3 papers
cs.CL2026
UniVer: A Unified Perspective for Multi-step and Multi-draft Speculative Decoding
Yepeng Weng, Qiao Hu, Takehisa Yairi
Speculative decoding accelerates Large Language Models via draft-then-verify, where verification can be framed as an Optimal Transport (OT) problem. Existing approaches typically h…
cs.CL2025
Traversal Verification for Speculative Tree Decoding
Yepeng Weng, Qiao Hu, Xujie Chen +5
Speculative decoding is a promising approach for accelerating large language models. The primary idea is to use a lightweight draft model to speculate the output of the target mode…
cs.LG2025
Hierarchical graph sampling based minibatch learning with chain preservation and variance reduction
Qia Hu, Bo Jiao
Graph sampling-based Graph Convolutional Networks (GCNs) decouple sampling from forward and backward propagation during minibatch training, enhancing scalability with respect to la…