Replacement Learning replaces selected blocks in CNNs and ViTs with learnable parameter-fusion surrogates derived from adjacent layers to reduce full-depth backpropagation redundancy.
Advancing supervised local learning beyond classification with long-term feature bank
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
LoPT achieves competitive task performance in LLM post-training by limiting task gradients to the upper model half and training the lower half with local feature reconstruction.
citing papers explorer
-
Replacement Learning: Training Neural Networks with Fewer Parameters
Replacement Learning replaces selected blocks in CNNs and ViTs with learnable parameter-fusion surrogates derived from adjacent layers to reduce full-depth backpropagation redundancy.
-
Rethinking Local Learning: A Cheaper and Faster Recipe for LLM Post-Training
LoPT achieves competitive task performance in LLM post-training by limiting task gradients to the upper model half and training the lower half with local feature reconstruction.