Inference-Friendly Models With MixAttention
Paper • 2409.15012 • Published
Vitaliy
vchiley
·
AI & ML interests
None yet
Organizations
authored a
paper over 1 year ago
authored 6
papers about 2 years ago
LoRA Learns Less and Forgets Less
Paper • 2405.09673 • Published • 91
Online Normalization for Training Neural Networks
Paper • 1905.05894 • Published
Pipelined Backpropagation at Scale: Training Large Models without Batches
Paper • 2003.11666 • Published
Memory Efficient 3D U-Net with Reversible Mobile Inverted Bottlenecks for Brain Tumor Segmentation
Paper • 2104.09648 • Published
Adaptive Braking for Mitigating Gradient Delay
Paper • 2007.01397 • Published
RevBiFPN: The Fully Reversible Bidirectional Feature Pyramid Network
Paper • 2206.14098 • Published