Assistant Professor, Eindhoven University of Technology
3 papers at NeurIPS 2025
xLSTM-Mixer integrates temporal, joint, and multi-view mixing with xLSTM blocks, achieving consistent SOTA performance in a wide range of long-term forecasting tasks.
GC-xLSTM jointly optimizes a sparse feature selector and predictive xLSTM to uncover a graph of Granger Causal dependencies
