LightToken: A Task and Model-agnostic Lightweight Token Embedding Framework for Pre-trained Language Models
Haoyu Wang, Ruirui Li, Haoming Jiang, Zhengyang Wang, Xianfeng Tang, Bin Bi, Monica Xiao Cheng, Bing Yin, Yaqing Wang, Tuo Zhao, Jing Gao
2023年份
5被引次数
问问这篇 Paper
问问你的智能体。
Lune 读过与它相关的顶会 Paper，每个回答都会注明依据哪几篇。
相关 Paper
- Token Distillation: Attention-Aware Input Embeddings for New TokensKonstantin Dobler, Desmond Elliott, Gerard de MeloICLR 2026 · 被引用 7 次
- Zero-Shot Tokenizer TransferBenjamin Minixhofer, Edoardo Maria Ponti, Ivan VulicNeurIPS 2024 · 被引用 37 次
- MPCFORMER: Fast, Performant and Provate Transformer Inference with MPCDacheng Li, Hongyi Wang, Rulin Shao, Han Guo 等ICLR 2023
- Convolutions and Self-Attention: Re-interpreting Relative Positions in Pre-trained Language ModelsTyler A. Chang, Yifan Xu, Weijian Xu, Zhuowen TuACL 2021
- Context-level Language Modeling by Learning Predictive Context Embeddingsbeiya dai, Yuliang Liu, Yunchong Song, Daozheng Xue 等ICML 2026 · 被引用 5 次
