Spurious Correlation-Aware Embedding Regularization for Worst-Group Robustness
arXiv:2511.04401v1 Announce Type: cross Abstract: Deep learning models achieve strong performance across various domains but often rely on spurious correlations,…
For An Exciting Tomorrow
arXiv:2511.04401v1 Announce Type: cross Abstract: Deep learning models achieve strong performance across various domains but often rely on spurious correlations,…
arXiv:2511.03227v2 Announce Type: replace-cross Abstract: We present a node-based storytelling system for multimodal content generation. The system represents stories as…
arXiv:2511.02997v1 Announce Type: new Abstract: As AI systems become more capable and widely deployed as agents, ensuring their safe operation…
arXiv:2511.02802v2 Announce Type: replace-cross Abstract: Tabular foundation models represent a growing paradigm in structured data learning, extending the benefits of…
arXiv:2511.03685v1 Announce Type: cross Abstract: Post-hoc recalibration methods are widely used to ensure that classifiers provide faithful probability estimates. We…