AIM applies modality-specific masks to balance stability and plasticity in asymmetric VLMs, achieving SOTA average performance and reduced forgetting on continual VQA v2 and GQA while preserving generalization to novel compositions.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A hybrid EWC+Replay spiking neural network achieves 0.979 average F1 score with near-zero forgetting on sequential nuclear ICS anomaly detection while using 12.6x fewer operations than an ANN.
citing papers explorer
-
AIM: Asymmetric Information Masking for Visual Question Answering Continual Learning
AIM applies modality-specific masks to balance stability and plasticity in asymmetric VLMs, achieving SOTA average performance and reduced forgetting on continual VQA v2 and GQA while preserving generalization to novel compositions.
-
Neuromorphic Continual Learning for Sequential Deployment of Nuclear Plant Monitoring Systems
A hybrid EWC+Replay spiking neural network achieves 0.979 average F1 score with near-zero forgetting on sequential nuclear ICS anomaly detection while using 12.6x fewer operations than an ANN.