9 papers
Reversible Lifelong Model Editing via Semantic Routing-Based LoRA
Haihua Luo, Xuming Ran, Tommi Kärkkäinen +4
The dynamic evolution of real-world necessitates model editing within Large Language Models. While existing methods explore modular isolation or parameter-efficient strategies, the…
A Simple Efficiency Incremental Learning Framework via Vision-Language Model with Nonlinear Multi-Adapters
Haihua Luo, Xuming Ran, Jiangrong Shen +5
Incremental Learning (IL) aims to learn new tasks while preserving previously acquired knowledge. Integrating the zero-shot learning capabilities of pre-trained vision-language mod…
Key-Value Pair-Free Continual Learner via Task-Specific Prompt-Prototype
Haihua Luo, Xuming Ran, Zhengji Li +6
Continual learning aims to enable models to acquire new knowledge while retaining previously learned information. Prompt-based methods have shown remarkable performance in this dom…
Spiking Neural Networks with Temporal Attention-Guided Adaptive Fusion for imbalanced Multi-modal Learning
Jiangrong Shen, Yulin Xie, Qi Xu +3
Multimodal spiking neural networks (SNNs) hold significant potential for energy-efficient sensory processing but face critical challenges in modality imbalance and temporal misalig…
Self-cross Feature based Spiking Neural Networks for Efficient Few-shot Learning
Qi Xu, Junyang Zhu, Dongdong Zhou +4
Deep neural networks (DNNs) excel in computer vision tasks, especially, few-shot learning (FSL), which is increasingly important for generalizing from limited examples. However, DN…
Efficient ANN-SNN Conversion with Error Compensation Learning
Chang Liu, Jiangrong Shen, Xuming Ran +4
Artificial neural networks (ANNs) have demonstrated outstanding performance in numerous tasks, but deployment in resource-constrained environments remains a challenge due to their…