MaCP: Minimal yet Mighty Adaptation via Hierarchical Cosine Projection
Open Access
- 1 January 2025
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 20602-20618
Abstract
Yixian Shen, Qi Bi, Jia-hong Huang, Hongyi Zhu, Andy D. Pimentel, Anuj Pathania. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Parameter-Efficient Fine-Tuning without Introducing New Latency2023
- Do Long-Range Language Models Actually Use Long-Range Context?2021
- The Power of Scale for Parameter-Efficient Prompt Tuning2021
- AdapterFusion: Non-Destructive Task Composition for Transfer Learning2021
- Completing density functional theory by machine learning hidden messages from moleculesnpj Computational Materials, 2020
- Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning2020
- HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training2020
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension2020
- EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover ClassificationIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019
- Exact Joint Sparse Frequency Recovery via Optimization MethodsIEEE Transactions on Signal Processing, 2016