Contribution Weights combine attention, value magnitude, and directional alignment to measure token influence more faithfully than attention alone, and show attention sinks actively suppress information via a convex sink-rate to output-norm relationship.
Logit standardization in knowledge distillation, 2024
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
APRIL-MedSeg is a new open-source modular toolbox that uses YAML configuration and component registries to unify multiple advanced paradigms for medical image segmentation.
A plug-and-play KL regularizer that masks the target token and renormalizes probabilities to improve the learning-forgetting trade-off in LoRA adaptation of LLMs.
citing papers explorer
-
Contribution Weights: A Geometrical Analysis of Self-Attention Transformers
Contribution Weights combine attention, value magnitude, and directional alignment to measure token influence more faithfully than attention alone, and show attention sinks actively suppress information via a convex sink-rate to output-norm relationship.
-
APRIL-MedSeg: A Modular Medical Image Segmentation Toolbox Embracing Modern Paradigms
APRIL-MedSeg is a new open-source modular toolbox that uses YAML configuration and component registries to unify multiple advanced paradigms for medical image segmentation.
-
Mask the Target: A Plug-and-Play Regularizer Against LoRA Forgetting
A plug-and-play KL regularizer that masks the target token and renormalizes probabilities to improve the learning-forgetting trade-off in LoRA adaptation of LLMs.