13 citations · 15 across the 5 of their papers we have counts for
4 papers · 1 filter
Efficiently Approximating Attention Is Hard
Lukas Haverbeck, Carmen Amo Alonso, Andres Felipe Posada-Moreno +2
Softmax attention is ubiquitous in modern machine learning, but its quadratic scaling with sequence length makes it costly. To reduce this cost, attention is often approximated wit…
The risk of KV cache compression
Lukas Haverbeck, Carmen Amo Alonso, Andres Felipe Posada-Moreno +2
Transformer inference on long sequences is expensive because softmax attention repeatedly reads from a large KV cache. The prevalent approach to this bottleneck is KV cache compres…
Concept Extraction for Time Series with ECLAD-ts
Antonia Holzapfel, Andres Felipe Posada-Moreno, Sebastian Trimpe
Convolutional neural networks (CNNs) for time series classification (TSC) are being increasingly used in applications ranging from quality prediction to medical diagnosis. The blac…
On Foundation Models for Dynamical Systems from Purely Synthetic Data
Martin Ziegler, Andres Felipe Posada-Moreno, Friedrich Solowjow +1
Foundation models have demonstrated remarkable generalization, data efficiency, and robustness properties across various domains. In this paper, we explore the feasibility of found…