PhD student, Technische Universität Darmstadt
2 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.
We introduce EmoNet-Face, a suite of diverse, AI-generated facial emotion datasets with a novel 40-category taxonomy, to improve AI's ability to understand human emotions more accurately and empathetically.
