6 papers
Dynamical Adapter Fusion: Constructing A Global Adapter for Pre-Trained Model-based Class-Incremental Learning
Ruiqi Liu, Boyu Diao, Zijia An +3
Class-Incremental Learning (CIL) requires models to continuously acquire new classes without forgetting previously learned ones. A dominant paradigm involves freezing a pre-trained…
CBPNet: A Continual Backpropagation Prompt Network for Alleviating Plasticity Loss on Edge Devices
Runjie Shao, Boyu Diao, Zijia An +2
To meet the demands of applications like robotics and autonomous driving that require real-time responses to dynamic environments, efficient continual learning methods suitable for…
PrePrompt: Predictive prompting for class incremental learning
Libo Huang, Zhulin An, Chuanguang Yang +5
Class Incremental Learning (CIL) based on pre-trained models offers a promising direction for open-world continual learning. Existing methods typically rely on correlation-based st…
A Nonlinear Hash-based Optimization Method for SpMV on GPUs
Chen Yan, Boyu Diao, Hangda Liu +2
Sparse matrix-vector multiplication (SpMV) is a fundamental operation with a wide range of applications in scientific computing and artificial intelligence. However, the large scal…
Efficient Continual Learning through Frequency Decomposition and Integration
Ruiqi Liu, Boyu Diao, Libo Huang +4
Continual learning (CL) aims to learn new tasks while retaining past knowledge, addressing the challenge of forgetting during task adaptation. Rehearsal-based methods, which replay…
Gensor: A Graph-based Construction Tensor Compilation Method for Deep Learning
Hangda Liu, Boyu Diao, Yu Yang +3
High-performance deep learning depends on efficient tensor programs. In recent years, automatic tensor program optimization, also known as tensor compilation, has emerged as the pr…