Picture for Filip Szatkowski

Filip Szatkowski

Sparser, Better, Deeper, Stronger: Improving Sparse Training with Exact Orthogonal Initialization

Add code
Jun 03, 2024
Viaarxiv icon

Accelerated Inference and Reduced Forgetting: The Dual Benefits of Early-Exit Networks in Continual Learning

Add code
Mar 12, 2024
Viaarxiv icon

Exploiting Transformer Activation Sparsity with Dynamic Inference

Add code
Oct 06, 2023
Viaarxiv icon

Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-free Continual Learning

Add code
Aug 18, 2023
Viaarxiv icon

Hypernetworks build Implicit Neural Representations of Sounds

Add code
Feb 17, 2023
Viaarxiv icon

HyperSound: Generating Implicit Neural Representations of Audio Signals with Hypernetworks

Add code
Nov 03, 2022
Viaarxiv icon

Progressive Latent Replay for efficient Generative Rehearsal

Add code
Jul 05, 2022
Figure 1 for Progressive Latent Replay for efficient Generative Rehearsal
Figure 2 for Progressive Latent Replay for efficient Generative Rehearsal
Figure 3 for Progressive Latent Replay for efficient Generative Rehearsal
Figure 4 for Progressive Latent Replay for efficient Generative Rehearsal
Viaarxiv icon