Attention mechanisms trained on Gaussian data learn parameters aligned with the principal eigenvectors of the covariance matrix, establishing an explicit link to PCA in both finite and infinite prompt regimes.
Journal of Mathematical Biology15(3), 267–273 (1982)
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
Direction maps and pinwheel structures in MT emerge spontaneously when a spatiotemporal deep network is trained on videos with contrastive self-supervised learning and spatial regularization.
OjaKV introduces hybrid full-rank storage for key tokens combined with online low-rank KV cache compression via Oja's algorithm to support memory-efficient long-context LLM inference.
MPCS integrates eleven plasticity mechanisms and reaches a Normalized Efficiency Score of 94.2 on a 31-task benchmark, with ablations showing that removing EWC and Hebbian updates yields higher performance at lower cost.
citing papers explorer
-
Attention-based PCA
Attention mechanisms trained on Gaussian data learn parameters aligned with the principal eigenvectors of the covariance matrix, establishing an explicit link to PCA in both finite and infinite prompt regimes.
-
Self-organized MT Direction Maps Emerge from Spatiotemporal Contrastive Optimization
Direction maps and pinwheel structures in MT emerge spontaneously when a spatiotemporal deep network is trained on videos with contrastive self-supervised learning and spatial regularization.
-
OjaKV: Context-Aware Online Low-Rank KV Cache Compression
OjaKV introduces hybrid full-rank storage for key tokens combined with online low-rank KV cache compression via Oja's algorithm to support memory-efficient long-context LLM inference.
-
MPCS: Neuroplastic Continual Learning via Multi-Component Plasticity and Topology-Aware EWC
MPCS integrates eleven plasticity mechanisms and reaches a Normalized Efficiency Score of 94.2 on a 31-task benchmark, with ablations showing that removing EWC and Hebbian updates yields higher performance at lower cost.