Warpax toolkit demonstrates that observer-robust optimization finds more extensive and severe energy-condition violations in warp drive metrics than single-frame Eulerian analysis.
Equinox: neural networks in JAX via callable PyTrees and filtered transformations
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
AMIGO is an end-to-end differentiable forward model of JWST AMI that corrects detector systematics to recover high-precision astrometry and detect close high-contrast companions.
NHODE framework learns partially observed dynamical systems by combining Hamiltonian neural networks with neural ODEs, enforcing energy conservation and improving long-horizon stability over data-driven baselines on mass-spring and three-body problems.
COALA applies convex optimization reformulations of neural networks to direct preference optimization, claiming single-GPU training with ~18% of DPO's TFLOPs and competitive performance on multiple datasets and models up to 8B parameters.
Predictive coding is recast as deep hierarchical Gaussian filters to restore precision-weighted message passing, yielding closed-form inference and online precision learning that matches backpropagation speed on FashionMNIST while outperforming on online and concept-drift tasks.
A framework based on linear dynamical systems unifies fixed-point iteration schemes such as Newton, Picard, and Jacobi as approximate linearizations of nonlinear recursions for parallelizing sequential models.
GCImOpt trains compact goal-conditioned neural policies by imitating efficiently generated optimal trajectories, achieving high success rates and near-optimal performance on cart-pole, quadcopter, and robot arm tasks while running thousands of times faster than optimization solvers.
A unified taxonomy of uncertainty in ML for physics is introduced together with validation tools such as coverage, calibration, and proper scoring rules, illustrated on regression and classification tasks.
jNO introduces a unified JAX tracing system for data-driven and physics-informed neural operator training that compiles domains, residuals, losses, and diagnostics into one pipeline.
citing papers explorer
-
Observer-robust energy condition verification for warp drive spacetimes
Warpax toolkit demonstrates that observer-robust optimization finds more extensive and severe energy-condition violations in warp drive metrics than single-frame Eulerian analysis.
-
AMIGO: a Data-Driven Calibration of the JWST Interferometer
AMIGO is an end-to-end differentiable forward model of JWST AMI that corrects detector systematics to recover high-precision astrometry and detect close high-contrast companions.
-
Learning partially observed systems with neural Hamiltonian ordinary differential equations
NHODE framework learns partially observed dynamical systems by combining Hamiltonian neural networks with neural ODEs, enforcing energy conservation and improving long-horizon stability over data-driven baselines on mass-spring and three-body problems.
-
Convex Optimization for Alignment and Preference Learning on a Single GPU
COALA applies convex optimization reformulations of neural networks to direct preference optimization, claiming single-GPU training with ~18% of DPO's TFLOPs and competitive performance on multiple datasets and models up to 8B parameters.
-
Closed-form predictive coding via hierarchical Gaussian filters
Predictive coding is recast as deep hierarchical Gaussian filters to restore precision-weighted message passing, yielding closed-form inference and online precision learning that matches backpropagation speed on FashionMNIST while outperforming on online and concept-drift tasks.
-
A Unifying Framework for Parallelizing Sequential Models with Linear Dynamical Systems
A framework based on linear dynamical systems unifies fixed-point iteration schemes such as Newton, Picard, and Jacobi as approximate linearizations of nonlinear recursions for parallelizing sequential models.
-
GCImOpt: Learning efficient goal-conditioned policies by imitating optimal trajectories
GCImOpt trains compact goal-conditioned neural policies by imitating efficiently generated optimal trajectories, achieving high success rates and near-optimal performance on cart-pole, quadcopter, and robot arm tasks while running thousands of times faster than optimization solvers.
-
Uncertainty in Physics and AI: Taxonomy, Quantification, and Validation
A unified taxonomy of uncertainty in ML for physics is introduced together with validation tools such as coverage, calibration, and proper scoring rules, illustrated on regression and classification tasks.
-
jNO: A JAX Library for Neural Operator and Foundation Model Training
jNO introduces a unified JAX tracing system for data-driven and physics-informed neural operator training that compiles domains, residuals, losses, and diagnostics into one pipeline.