Announcement_22

Four papers accepted at NeurIPS 2026, including one oral presentation! “Spectral Energy Allocation Enables Source-Free Domain Adaptation in Time Series Forecasting” (Oral), “Beyond Feature Disruption: Boundary-Diverting Unlearnable Examples against Linear Probing”, “Unsupervised Unlearnable Segmentation via Semantic Structure Disruption”, and “From Small to Large: Cross-Scale Graph Domain Adaptation via Local-Global Structural Alignment”. Congratulations to all my co-authors!