Combining Hierarchical Cognitive Process with Process Supervision for Interpretable Scene Safety UnderstandingResearchSep 23, 2026
A Semiotics-Aware Framework for Evaluating Fidelity and Coverage in Natural Language GenerationResearchSep 23, 2026
Beyond Scalar Sensitivity: Activation-Aware Mixed-Precision LLM Quantization with Cross-Layer RefinementResearchSep 23, 2026
How to Estimate Whether You Have Found Several Needles in a Haystack: Measuring Calibration in Multi-Label Text ClassificationResearchSep 23, 2026
Certified Against Which Oracle? Execution Labels Set the Reported Risk of Conformal Abstention for Text-to-SQLResearchSep 23, 2026
Interweaving Marginals into Multivariate Sample Paths: Training-Free Dependence Construction for Probabilistic Time Series Foundation ModelsResearchSep 23, 2026