Calibrated Decomposition of Aleatoric and Epistemic Uncertainty in Deep Features for Inference-Time Adaptation

Documenti analoghi

• TRIAGE: Type-Routed Interventions via Aleatoric-Epistemic Gated Estimation in Robotic Manipulation and Adaptive Perception -- Don't Treat All Uncertainty the Same
  di: Kumar, Divake, et al.
  Pubblicazione: (2026)
• VLM Judges Can Rank but Cannot Score: Task-Dependent Uncertainty in Multimodal Evaluation
  di: Kumar, Divake, et al.
  Pubblicazione: (2026)
• Uncertainty-Guided Inference-Time Depth Adaptation for Transformer-Based Visual Tracking
  di: Poggi, Patrick, et al.
  Pubblicazione: (2026)
• INTACT: Inducing Noise Tolerance through Adversarial Curriculum Training for LiDAR-based Safety-Critical Perception and Autonomy
  di: Darabi, Nastaran, et al.
  Pubblicazione: (2025)
• EigenShield: Causal Subspace Filtering via Random Matrix Theory for Adversarially Robust Vision-Language Models
  di: Darabi, Nastaran, et al.
  Pubblicazione: (2025)