AIS framework with time-varying piecewise parameters and hidden states enables analog hardware to perform generative modeling, achieving FID 27.6 on MNIST and 80.8 on Fashion-MNIST with 23uJ per image using 4-bit sparse architectures.
Title resolution pending
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 7verdicts
UNVERDICTED 7roles
background 2polarities
background 2representative citing papers
Codon optimization for mRNA is mapped to Ising/Potts sampling on thermodynamic hardware, achieving similar quality (~234-240 scores) with ~10^6 lower energy than GPU on SARS-CoV-2 spike protein.
Decomposes entropy production in OU processes into oscillatory and nonnormal parts with associated trade-offs, demonstrated on a bead-spring model.
Thermodynamic networks using non-equilibrium steady states achieve universal function approximation when engineered with negative differential conductance, as shown in quantum dot and enzymatic examples for sine fitting and MNIST classification.
A stochastic Tsetlin machine constructed from thermodynamic logic gates achieves classification accuracy statistically comparable to the conventional digital version.
Physical Foundation Models are fixed physical hardware realizations of foundation-scale neural networks that compute via inherent material dynamics, potentially delivering orders-of-magnitude gains in energy efficiency, speed, and density over digital systems.
No single post-Moore technology replaces current HPC for plasma simulations, but FPGA-class accelerators offer near-term kernel offload, non-von Neumann architectures medium-term operator acceleration, and quantum computing long-term potential for warm dense matter microphysics.
citing papers explorer
-
Generative Models on Analog Hardware with Dynamics
AIS framework with time-varying piecewise parameters and hidden states enables analog hardware to perform generative modeling, achieving FID 27.6 on MNIST and 80.8 on Fashion-MNIST with 23uJ per image using 4-bit sparse architectures.
-
Energy-efficient codon optimization on thermodynamic hardware
Codon optimization for mRNA is mapped to Ising/Potts sampling on thermodynamic hardware, achieving similar quality (~234-240 scores) with ~10^6 lower energy than GPU on SARS-CoV-2 spike protein.
-
Oscillatory-nonnormal decomposition of dissipation in Ornstein-Uhlenbeck processes
Decomposes entropy production in OU processes into oscillatory and nonnormal parts with associated trade-offs, demonstrated on a bead-spring model.
-
Thermodynamic Networks: Harnessing Non-Equilibrium Steady States for Computation
Thermodynamic networks using non-equilibrium steady states achieve universal function approximation when engineered with negative differential conductance, as shown in quantum dot and enzymatic examples for sine fitting and MNIST classification.
-
Interpretable rule-based learning in an autonomous thermodynamic network
A stochastic Tsetlin machine constructed from thermodynamic logic gates achieves classification accuracy statistically comparable to the conventional digital version.
-
Physical Foundation Models: Fixed hardware implementations of large-scale neural networks
Physical Foundation Models are fixed physical hardware realizations of foundation-scale neural networks that compute via inherent material dynamics, potentially delivering orders-of-magnitude gains in energy efficiency, speed, and density over digital systems.
-
Post-Moore Technologies for Plasma Simulation: A Community Roadmap
No single post-Moore technology replaces current HPC for plasma simulations, but FPGA-class accelerators offer near-term kernel offload, non-von Neumann architectures medium-term operator acceleration, and quantum computing long-term potential for warm dense matter microphysics.