Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling

Xianzhen Luo, Yixuan Wang, Qingfu Zhu, Zhiming Zhang, Xuanyu Zhang, Qing Yang, Dongliang Xu. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Authors

Publication Details

Published
2025-01-01
DOI
https://doi.org/10.18653/v1/2025.acl-long.338
Citations
1
Primary Topic
Natural Language Processing Techniques
Type
article
Field-Weighted Citation Impact
2.48

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling

Xianzhen Luo, Xuanyu Zhang, Zhiming Zhang, Dongliang Xu et al.
1 citations
Natural Language Processing Techniques
2.48
article

Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling

Xianzhen Luo, Xuanyu Zhang, Zhiming Zhang, Dongliang Xu, Yixuan Wang, Qingfu Zhu, Qing Yang
article en
1 citations

Abstract

Xianzhen Luo, Yixuan Wang, Qingfu Zhu, Zhiming Zhang, Xuanyu Zhang, Qing Yang, Dongliang Xu. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

National Natural Science Foundation of China
Openalex Percentile: Top 9%
Natural Language Processing Techniques
2.48
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.