A Jacobi diffusion on graphon space is discretized into a graph-level generative process that matches the continuous process's first moment exactly and second moment up to a closed-form gap, enabling out-of-scale graph generation.
Score-based generative modeling through stochastic differential equations
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
years
2026 7representative citing papers
EBMol is the first energy-based model for 3D molecular generation to reach state-of-the-art performance on QM9 and GEOM-Drugs by learning a physically grounded energy landscape without explicit simulation during training.
FaithfulFaces introduces a pose-faithful identity aligner with a shared dictionary and invariance constraint to maintain facial identity in text-to-video generation under large pose changes and occlusions.
Causality-encoded diffusion models use a known DAG to train graph-consistent conditional diffusions for observational recovery, interventional sampling via fixed-variable propagation, and a resampling-based directed edge test with convergence rates depending on local dimension.
RIDER improves RNA 3D structural similarity by over 100% using RL-guided diffusion and discovers non-native sequence designs.
3D-GeoFlow reformulates discrete categorical 3D geological generation as simulation-free continuous vector field regression with 3D attention gates, claiming to outperform heuristics and diffusion models on a 2,200-case synthetic dataset.
The paper surveys AI surrogates including PINNs, neural operators, and hybrid generative models as ways to reach high-Re and high-S MHD regimes beyond direct numerical simulation.
citing papers explorer
-
DiPhon: Diffusion on Graphons for Scalable Graph Generation
A Jacobi diffusion on graphon space is discretized into a graph-level generative process that matches the continuous process's first moment exactly and second moment up to a closed-form gap, enabling out-of-scale graph generation.
-
Generating Physically Consistent Molecules with Energy-Based Models
EBMol is the first energy-based model for 3D molecular generation to reach state-of-the-art performance on QM9 and GEOM-Drugs by learning a physically grounded energy landscape without explicit simulation during training.
-
FaithfulFaces: Pose-Faithful Facial Identity Preservation for Text-to-Video Generation
FaithfulFaces introduces a pose-faithful identity aligner with a shared dictionary and invariance constraint to maintain facial identity in text-to-video generation under large pose changes and occlusions.
-
Causality-Encoded Diffusion Models for Interventional Sampling and Edge Inference
Causality-encoded diffusion models use a known DAG to train graph-consistent conditional diffusions for observational recovery, interventional sampling via fixed-variable propagation, and a resampling-based directed edge test with convergence rates depending on local dimension.
-
RIDER: 3D RNA Inverse Design with Reinforcement Learning-Guided Diffusion
RIDER improves RNA 3D structural similarity by over 100% using RL-guided diffusion and discovers non-native sequence designs.
-
Attention-Guided Flow-Matching for Sparse 3D Geological Generation
3D-GeoFlow reformulates discrete categorical 3D geological generation as simulation-free continuous vector field regression with 3D attention gates, claiming to outperform heuristics and diffusion models on a 2,200-case synthetic dataset.
-
Magnetohydrodynamics Simulations
The paper surveys AI surrogates including PINNs, neural operators, and hybrid generative models as ways to reach high-Re and high-S MHD regimes beyond direct numerical simulation.