Langevin sampling on the modern Hopfield energy produces training-free stochastic attention that transitions from exact retrieval to generation as temperature rises, with an entropy inflection condition marking the shift.
Title resolution pending
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 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
New discrete-time approximations to SG(L)D enable accurate non-asymptotic predictions of covariance and integrated autocorrelation time for practical tuning in large-batch or misspecified regimes.
VSLP infers dense segmentations from global label proportions via a pre-trained transformer for initial confidence maps followed by variational optimization using Wasserstein fidelity and a learned regularizer, outperforming prior weakly supervised methods on histopathology datasets.
General criteria extend L^p-mean Wasserstein convergence rates of occupation measures to non-stationary or non-Markovian ergodic processes under conditional convergence to equilibrium, with applications to Brownian diffusions and fractional Brownian driven SDEs.
citing papers explorer
-
Stochastic Attention via Langevin Dynamics on the Modern Hopfield Energy
Langevin sampling on the modern Hopfield energy produces training-free stochastic attention that transitions from exact retrieval to generation as temperature rises, with an entropy inflection condition marking the shift.
-
Accurate Large-sample Uncertainty Quantification using Stochastic Gradient Markov Chain Monte Carlo
New discrete-time approximations to SG(L)D enable accurate non-asymptotic predictions of covariance and integrated autocorrelation time for practical tuning in large-batch or misspecified regimes.
-
Semantic Segmentation for Histopathology using Learned Regularization based on Global Proportions
VSLP infers dense segmentations from global label proportions via a pre-trained transformer for initial confidence maps followed by variational optimization using Wasserstein fidelity and a learned regularizer, outperforming prior weakly supervised methods on histopathology datasets.
-
Convergence rate of the occupation measure of classes of ergodic processes toward their invariant distribution in mean Wasserstein distance
General criteria extend L^p-mean Wasserstein convergence rates of occupation measures to non-stationary or non-Markovian ergodic processes under conditional convergence to equilibrium, with applications to Brownian diffusions and fractional Brownian driven SDEs.