1 citations · 1 across the 4 of their papers we have counts for
7 papers
ConceptCF: Concept-based Counterfactuals for the Explainability of Time Series
Annemarie Jutte, Faizan Ahmed, Jeroen Linssen +1
This paper proposes ConceptCF, a method for counterfactual generation that operates on human-interpretable concepts. In high-stakes domains such as healthcare and predictive mainte…
When Data Is Scarce: Scaling Sparse Language Models with Repeated Training
Boqian Wu, Qiao Xiao, Patrik Okanovic +6
Scaling laws for dense LLMs under infinite data are well explored, but how sparsity interacts with limited data is not. In this work, we study sparse training in data-constrained r…
Memory-Efficient LLM Training with Dynamic Sparsity: From Stability to Practical Scaling
Qiao Xiao, Boqian Wu, Patrik Okanovic +6
Dynamic Sparse Training (DST) offers a promising paradigm for improving the training and inference efficiency of deep neural networks; however, we find that in large language model…
C-SHAP for time series: An approach to high-level temporal explanations
Annemarie Jutte, Faizan Ahmed, Jeroen Linssen +1
In high-stakes domains, such as healthcare and industry, the explainability of AI-based decision-making has become crucial. Without insight into model reasoning, the reliability of…
Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption Robustness
Boqian Wu, Qiao Xiao, Shunxin Wang +5
It is generally perceived that Dynamic Sparse Training opens the door to a new era of scalability and efficiency for artificial neural networks at, perhaps, some costs in accuracy…
E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentation
Boqian Wu, Qiao Xiao, Shiwei Liu +5
Deep neural networks have evolved as the leading approach in 3D medical image segmentation due to their outstanding performance. However, the ever-increasing model size and computa…