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
Learning an Anchored Prompt Space for Continual Adaptation of Large Language ModelsResearchSep 29, 2026