Picture for Andrii Skliar

Andrii Skliar

Efficient LLM Inference using Dynamic Input Pruning and Cache-Aware Masking

Add code
Dec 02, 2024
Viaarxiv icon

Mixture of Cache-Conditional Experts for Efficient Mobile Device Inference

Add code
Nov 27, 2024
Viaarxiv icon

Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding

Add code
Feb 26, 2024
Viaarxiv icon

Hyperbolic Convolutional Neural Networks

Add code
Aug 29, 2023
Viaarxiv icon

Revisiting Single-gated Mixtures of Experts

Add code
Apr 11, 2023
Viaarxiv icon

Simple and Efficient Architectures for Semantic Segmentation

Add code
Jun 16, 2022
Figure 1 for Simple and Efficient Architectures for Semantic Segmentation
Figure 2 for Simple and Efficient Architectures for Semantic Segmentation
Figure 3 for Simple and Efficient Architectures for Semantic Segmentation
Figure 4 for Simple and Efficient Architectures for Semantic Segmentation
Viaarxiv icon

Cyclical Pruning for Sparse Neural Networks

Add code
Feb 02, 2022
Figure 1 for Cyclical Pruning for Sparse Neural Networks
Figure 2 for Cyclical Pruning for Sparse Neural Networks
Figure 3 for Cyclical Pruning for Sparse Neural Networks
Figure 4 for Cyclical Pruning for Sparse Neural Networks
Viaarxiv icon

Distilling Optimal Neural Networks: Rapid Search in Diverse Spaces

Add code
Dec 16, 2020
Figure 1 for Distilling Optimal Neural Networks: Rapid Search in Diverse Spaces
Figure 2 for Distilling Optimal Neural Networks: Rapid Search in Diverse Spaces
Figure 3 for Distilling Optimal Neural Networks: Rapid Search in Diverse Spaces
Figure 4 for Distilling Optimal Neural Networks: Rapid Search in Diverse Spaces
Viaarxiv icon