Reformulates constrained black-box optimization as posterior inference in latent space of flow-based models amortized by outsourced diffusion models, claiming superior performance on synthetic and real tasks.
Simple and scalable predictive uncertainty estimation using deep ensembles
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
HyRe personalizes reward models at test time by reweighting an ensemble of heads trained on aggregate preferences, using few target examples to outperform uniform averaging and prior methods on RewardBench and 32 tasks.
Uncertainty-aware fine-tuning with a decision-theory-based loss produces better-calibrated uncertainty estimates than standard training on free-form QA tasks.
Integrates Dirichlet-based class probability modeling into MC Dropout to improve calibration of uncertainty estimates while preserving efficiency.
citing papers explorer
-
Posterior Inference in Latent Space for Scalable Constrained Black-box Optimization
Reformulates constrained black-box optimization as posterior inference in latent space of flow-based models amortized by outsourced diffusion models, claiming superior performance on synthetic and real tasks.
-
Test-Time Alignment via Hypothesis Reweighting
HyRe personalizes reward models at test time by reweighting an ensemble of heads trained on aggregate preferences, using few target examples to outperform uniform averaging and prior methods on RewardBench and 32 tasks.
-
Enhancing Trust in Large Language Models via Uncertainty-Calibrated Fine-Tuning
Uncertainty-aware fine-tuning with a decision-theory-based loss produces better-calibrated uncertainty estimates than standard training on free-form QA tasks.
-
Dirichlet-Based Monte Carlo Dropout for Uncertainty Estimation in Neural Networks
Integrates Dirichlet-based class probability modeling into MC Dropout to improve calibration of uncertainty estimates while preserving efficiency.