Stochastic Attention adds calibrated uncertainty to transformer foundation models through inference-time multinomial sampling of attention weights and univariate post-hoc tuning of a concentration parameter.
Algorithmic Learning in a Random World
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4roles
background 1polarities
background 1representative citing papers
Coupling-Grouped XY-QAOA enables joint anomaly-feature selection via a constraint-preserving grouped-angle QAOA variant, achieving 45.9-61.3% circuit depth reduction and larger feasible executions (64 qubits at p=2) on IBM Heron hardware compared to standard approaches.
Conformal prediction generates valid sets of future conflict state sequences under a Markov assumption, providing robust uncertainty quantification compared to point predictions from likelihood methods.
citing papers explorer
-
Calibrating Scientific Foundation Models with Inference-Time Stochastic Attention
Stochastic Attention adds calibrated uncertainty to transformer foundation models through inference-time multinomial sampling of attention weights and univariate post-hoc tuning of a concentration parameter.
-
Coupling-Grouped XY-QAOA for Joint Anomaly-Feature Selection
Coupling-Grouped XY-QAOA enables joint anomaly-feature selection via a constraint-preserving grouped-angle QAOA variant, achieving 45.9-61.3% circuit depth reduction and larger feasible executions (64 qubits at p=2) on IBM Heron hardware compared to standard approaches.
-
Conflict Forecasting via Conformal Prediction for Markov Processes
Conformal prediction generates valid sets of future conflict state sequences under a Markov assumption, providing robust uncertainty quantification compared to point predictions from likelihood methods.
- Conformalized Quantum DeepONet Ensembles for Scalable Operator Learning with Distribution-Free Uncertainty