Memory Efficient Continual Learning with Transformers
–Neural Information Processing Systems
To address the issue of incremental fine-tuning of pre-trained Transformers in the sequential learning setting without CF, we propose Adaptive Distillation of Adapters (ADA).
Neural Information Processing Systems
Aug-14-2025, 12:44:37 GMT
- Genre:
- Research Report > New Finding (0.46)
- Industry:
- Education (0.68)
- Technology:
- Information Technology
- Artificial Intelligence
- Machine Learning > Neural Networks (1.00)
- Natural Language (1.00)
- Vision (0.70)
- Communications (1.00)
- Sensing and Signal Processing > Image Processing (0.68)
- Artificial Intelligence
- Information Technology