Showing 2025Show all
2 papers · 1 filter
cs.CL2025
LoLA: Low-Rank Linear Attention With Sparse Caching
Luke McDermott, Robert W. Heath, Rahul Parhi
The per-token cost of transformer inference scales with context length, preventing its application to lifelong in-context learning. Linear attention is an efficient alternative tha…
cs.LG2025
Finding Stable Subnetworks at Initialization with Dataset Distillation
Luke McDermott, Rahul Parhi
Recent works have shown that Dataset Distillation, the process for summarizing the training data, can be leveraged to accelerate the training of deep learning models. However, its…