NFL is a buffer-free continual learning framework that decomposes networks, applies stepwise freezing with knowledge distillation, and adds an auto-encoder in NFL+ to match replay-based performance on image benchmarks while using only 2.53% of the memory.
A comprehensive survey of forgetting in deep learning beyond continual learning, 2023
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.LG 2roles
other 1polarities
unclear 1representative citing papers
The paper introduces a new taxonomy for model merging methods and reviews their applications in LLMs, MLLMs, continual learning, multi-task learning, and other subfields while outlining open challenges.
citing papers explorer
-
No Forgetting Learning: Buffer-free Continual Learning Classification
NFL is a buffer-free continual learning framework that decomposes networks, applies stepwise freezing with knowledge distillation, and adds an auto-encoder in NFL+ to match replay-based performance on image benchmarks while using only 2.53% of the memory.
-
Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities
The paper introduces a new taxonomy for model merging methods and reviews their applications in LLMs, MLLMs, continual learning, multi-task learning, and other subfields while outlining open challenges.