Shell-horizon certificates are derived for decoded physical invariants in latent models, allowing conservation laws to survive representation learning via a monotone alignment from soft witnesses, with empirical support on lift and pixel observations where soft invariants outperform hard symplectic
Hamiltonian Generative Networks
7 Pith papers cite this work, alongside 29 external citations. Polarity classification is still indexing.
7
Pith papers citing it
29
external citations · external index
representative citing papers
A two-stage contrastive teacher-student framework learns and then projects latent dynamics onto port-Hamiltonian submanifolds from partial observations.
Neural ODEs reproduce 2RDM dynamics from data only when three-particle cumulant correlations are strong, mapping the validity regime of cumulant expansions.
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.
DINO decomposes turbulent evolution into parallel local differential and global integral operators to achieve stable autoregressive forecasting on 2D Kolmogorov flow.
PhysRAG curates 7K videos from WISA-80K, builds a physical video database, and injects knowledge via learnable queries into a diffusion model to reach SOTA visual quality and physical compliance on PhyGenBench and VBench.
citing papers explorer
-
When Do Conservation Laws Survive Learned Representations? Certified Horizons for Latent World Models
Shell-horizon certificates are derived for decoded physical invariants in latent models, allowing conservation laws to survive representation learning via a monotone alignment from soft witnesses, with empirical support on lift and pixel observations where soft invariants outperform hard symplectic
-
Identify Then Project: Contrastive Learning of Latent Dynamics from Partial Observations with Port-Hamiltonian Structure
A two-stage contrastive teacher-student framework learns and then projects latent dynamics onto port-Hamiltonian submanifolds from partial observations.
-
Capturing reduced-order quantum many-body dynamics out of equilibrium via neural ordinary differential equations
Neural ODEs reproduce 2RDM dynamics from data only when three-particle cumulant correlations are strong, mapping the validity regime of cumulant expansions.
-
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.
-
Differential-Integral Neural Operator for Long-Term Turbulence Forecasting
DINO decomposes turbulent evolution into parallel local differential and global integral operators to achieve stable autoregressive forecasting on 2D Kolmogorov flow.
-
PhysRAG: Enhancing Physics-Awareness in Video Generation via Retrieval-Augmented Generation
PhysRAG curates 7K videos from WISA-80K, builds a physical video database, and injects knowledge via learnable queries into a diffusion model to reach SOTA visual quality and physical compliance on PhyGenBench and VBench.
- Symplectic Neural Networks for Learning Non-Separable Hamiltonians