TCMQA: A 38K-Question Traditional Chinese Medicine Benchmark with a Licensed-Practitioner ReferenceResearchSep 29, 2026
When Should a Human Take Back Control? Optimal Delegation under Turbulent AI RiskResearchSep 29, 2026
UNMATCH: Selective Unbalanced Token-Patch Matching for Forensic Image-Claim VerificationResearchSep 29, 2026
From Scene Graphs to Answers: Selective Neuro-Symbolic Reasoning for Autonomous DrivingResearchSep 29, 2026
TeacherGRPO: Closing the Capacity Gap in Reasoning Distillation via Teacher AlignmentResearchSep 29, 2026