Self-Supervised Learning

NeurIPS 2026

Drive vs. Decay has been accepted at NeurIPS 2026 (Main Track). The paper studies JEPA training dynamics and representation collapse. The main conference will take place in Sydney on December 6–12, 2026.

Continue reading

Relational steering for tabular anomaly detection

Investigating whether context-dependent interventions in tabular models reveal anomalies that violate relationships between variables.

Continue reading