SwarmReconGuard: Black-Box Detection of Distributed Collective Reconnaissance by Individually Benign-Looking Agent PopulationsResearchOct 8, 2026
Sparse Feature Policy Unlearning Mitigates State Hallucination in Vision-Language-Action ModelsResearchOct 8, 2026
Package Hallucination Attacks on Coding Agents through Prompt Injection in Rule FilesResearchOct 8, 2026
TutorLoop: Regulating Student Learning Behaviors via Sensor-in-the-Loop Generative FeedbackResearchOct 8, 2026
UltraWorld: Learning Interactive Ultrasound World Models from Untracked Clinical Videos with Acoustic Sampling MapResearchOct 8, 2026
Concentration, Not Uncertainty: Why Targeted Synthetic Data Doesn't Help Camouflaged Object DetectionResearchOct 8, 2026