Hydra: Multi-head Low-rank Adaptation for Parameter Efficient Fine-tuning

1 code implementation • 13 Sep 2023 • Sanghyeon Kim, Hyunmo Yang, Younghyun Kim, Youngjoon Hong, Eunbyung Park

The recent surge in large-scale foundation models has spurred the development of efficient methods for adapting these models to various downstream tasks.

SMPConv: Self-moving Point Representations for Continuous Convolution

1 code implementation • CVPR 2023 • Sanghyeon Kim, Eunbyung Park

This paper suggests an alternative approach to building a continuous convolution without neural networks, resulting in more computationally efficient and improved performance.

Descriptive Sequential Image Classification +1