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.
Amit, Hanoch Gutfreund, and Haim Sompolinsky
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
DenseAMs show tradeoffs between entropy production, retrieval accuracy, and speed at intermediate loads, with a new failure mode in higher-order networks at finite temperature.
Asynchronous sequential updates in KLR Hopfield networks produce statistically indistinguishable trajectories from synchronous dynamics, achieve empirical capacities near P/N=30, and converge with event counts close to initial Hamming distance.
KLR Hopfield networks store up to 16-20 times their neuron count before dynamical instability from crosstalk noise causes collapse, with sharp attractor boundaries observed via morphing and SNR analysis.
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.
-
Stochastic Thermodynamics of Associative Memory
DenseAMs show tradeoffs between entropy production, retrieval accuracy, and speed at intermediate loads, with a new failure mode in higher-order networks at finite temperature.
-
Efficient event-driven retrieval in high-capacity kernel Hopfield networks
Asynchronous sequential updates in KLR Hopfield networks produce statistically indistinguishable trajectories from synchronous dynamics, achieve empirical capacities near P/N=30, and converge with event counts close to initial Hamming distance.
-
Geometric and dynamical analysis of attractor boundaries and storage limits in kernel Hopfield networks
KLR Hopfield networks store up to 16-20 times their neuron count before dynamical instability from crosstalk noise causes collapse, with sharp attractor boundaries observed via morphing and SNR analysis.