RCA is a training-free module that boosts input context signal strength in the residual stream of LLMs by orthogonal decoupling of attention routing from value magnitude.
arXiv preprint arXiv:2303.08084 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
SalUn uses gradient-based weight saliency to achieve effective machine unlearning of data, classes, or concepts in image classification and generation, narrowing the gap to exact retraining.
DebFilter mitigates biases in text-to-image diffusion models by applying a fixed offset to the guidance embedding slice in cross-attention during inference.
citing papers explorer
-
DebFilter: Eradicating Biases Stashed in Value
DebFilter mitigates biases in text-to-image diffusion models by applying a fixed offset to the guidance embedding slice in cross-attention during inference.