Structure-Guided Masked Autoencoders for Ultra-High Resolution Scientific Image UnderstandingResearchSep 28, 2026
MM-VeriAgent: Learning to Use Extensive Tools to Verify Multimodal Misinformation with Reinforcement LearningResearchSep 28, 2026
SAGE: Source-Anchored Guidance via Frequency Equalization for Hierarchical RGB-T Alignment and FusionResearchSep 28, 2026
HARDEN: Constrained Evolutionary Search for Harder, Answer-Preserving Evaluation CasesResearchSep 28, 2026
Combining General and Domain-Specific Pretext Tasks for Brain MR Image SegmentationResearchSep 28, 2026
VLALight: Lightweight Vision-Language-Action Models for Emergency-Aware Traffic Signal ControlResearchSep 28, 2026
LAVOIR: Teaching a Single-Pass Decision Encoder When and What to Ask with Amortized Value of InformationResearchSep 28, 2026