Risk-Averse Online POMDP Planning via CVaR of the Immediate Cost with Performance GuaranteesResearchSep 30, 2026
Representational Simplicity and Circuit Size Dissociate in a Threshold-Dependent Way: A Controlled Test via Adversarial TrainingResearchSep 30, 2026
More Programs or More Rolls? Separating Coverage from Specialization in LLM HarnessesResearchSep 30, 2026
Mirror-Score: Calibrated, Inference-only Scoring Exposes the Limits of Sequence-compatibility Ranking in D-peptide DesignResearchSep 30, 2026
Right Words, Wrong Moment: A Clinician-Grounded Analysis of Distress in 19,930 Conversations between Young People and ChatGPTResearchSep 30, 2026
GeoWind2Plan: Mission-Time 3D Urban Wind Prediction for Energy-Efficient UAV PlanningResearchSep 30, 2026
From Sharp Eyes to Expert Mind: Internalizing Expert Knowledge in MLLMs for Tampered Text DetectionResearchSep 30, 2026
From Distributions to Stochastic Processes: Neural Approximation of Measure-Valued MapsResearchSep 30, 2026
Rethinking Personalized Generation: Test-Time Alignment via Factorized Ranking ModelsResearchSep 30, 2026