Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
VIA-SD: Verification via Intra-Model Routing for Speculative Decoding
Yuchen Xian, Yang He, Yunqiu Xu +1
Speculative decoding (SD) addresses the high inference costs of LLMs by having lightweight drafters generate candidates for large verifiers to validate in parallel. Existing draft-…
cs.CL2025
Swift Cross-Dataset Pruning: Enhancing Fine-Tuning Efficiency in Natural Language Understanding
Binh-Nguyen Nguyen, Yang He
Dataset pruning aims to select a subset of a dataset for efficient model training. While data efficiency in natural language processing has primarily focused on within-corpus scena…