Task-Incremental Learning PLMs-based TIL Traditional Methods Continual Pre-training Methods Parameter-Efficient Tuning Methods Continual Sequence Generation with Adaptive Compositional Modules [paper] Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learning [paper] ...
It is well known natural images are well described as compositional hierarchies of a small set of primitive features. By learning a small set of primitive features at lower layers, multi-level SQHNs seem able to generalize these learned features across more data points, increasing capacity and ...
Azadi, S., Pathak, D., Ebrahimi, S., Darrell, T.: Compositional GAN: learning image-conditional binary composition. Int. J. Comput. Vis. 128, 2570–2585 (2020). https://doi.org/10.1007/s11263-020-01336-9 Article Google Scholar Blum, A., Mitchell, T.: Combining labeled and unlabel...
Continual Sequence Generation with Adaptive Compositional Modules [paper] Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learning [paper]Instruction Tuning-based MethodsPrompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialogue [paper]...