Routing Probes Can Improve Without New Information: An Exact-Null Audit of Uncertainty Beyond Model Outputs
cs.AI
Submitted: 2026-09-30
Updated: 2026-09-30
Sources
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Adaptive Computation Time for Recurrent Neural Networks
- Attention Residuals
- Probing Routing-Conditional Calibration in Attention-Residual Transformers
- Extracting Uncertainty Estimates from Mixtures of Experts for Semantic Segmentation
- A Theory of Usable Information Under Computational Constraints
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems