Work

TETRIS: Optimal Draft Token Selection for Batch Speculative Decoding

Year: 2025

Type: conference-paper

Abstract: Zhaoxuan Wu, Zijian Zhou, Arun Verma, Alok Prakash, Daniela Rus, Bryan Kian Hsiang Low. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Source: Annual Meeting of the Association for Computational Linguistics (ACL)

DOI: 10.18653/v1/2025.acl-long.1598

Authors: Zhaoxuan Wu, Zijian Zhou, Arun Verma, Alok Prakash, Daniela Rus, Bryan Kian Hsiang Low

Institutions: Singapore-MIT Alliance for Research and Technology, National University of Singapore, Massachusetts Institute of Technology

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: National Research Foundation

OpenAlex ID: W4412889591

FWCI:

Cites:

Cited by:

Related to: 10