A unified data reconstruction attack achieves provable finite-width recovery in random feature networks and efficient subspace-based reconstruction for general models using weight changes.
hub
Generative adversarial networks.Communications of the ACM, 63(11):139–144
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
hub tools
verdicts
UNVERDICTED 10representative citing papers
GRDM jointly generates relational database tables via graph-conditional diffusion without table ordering, outperforming autoregressive baselines on multi-hop correlations and single-table fidelity across six real RDBs.
Introduces a modular unified Lyapunov template for continuous-time analysis of minimax, bilevel (via penalty), and min-min-max problems with explicit time-scale thresholds.
Adversarial training improves PINNs by using the discriminator to mitigate spectral bias and stiffness, with a new NTK-based framework providing theoretical grounding and a practical algorithm.
RaPD enables resolution-agnostic image generation by diffusing in a semantics-enriched continuous Neural Image Field latent space using semantic guidance and a coordinate-queried attention renderer.
Intermediate layer embedding sensitivity to perturbations distinguishes AI-generated images from real ones, yielding higher AUROC on GenImage and Forensics Small benchmarks than prior methods.
Embedding Loss aligns feature distributions via MMD in random network embeddings to boost one-step diffusion distillation, reaching SOTA FID of 1.475 on CIFAR-10 unconditional generation.
EnFlow integrates flow-based conformer generation with energy landscape modeling to enable joint ensemble generation and ground-state identification using only 1-2 ODE steps.
RefTon is a flux-based virtual try-on method that uses unpaired reference images of the target garment on different people to guide texture and detail preservation in a streamlined person-to-person pipeline without body parsing or masks.
One-step pixel-MeanFlow models recover key galaxy morphology statistics at orders-of-magnitude lower computational cost than standard DDPM sampling while remaining weaker on fine-grained structure.
citing papers explorer
-
Efficient Techniques for Data Reconstruction, with Finite-Width Recovery Guarantees
A unified data reconstruction attack achieves provable finite-width recovery in random feature networks and efficient subspace-based reconstruction for general models using weight changes.
-
Joint Relational Database Generation via Graph-Conditional Diffusion Models
GRDM jointly generates relational database tables via graph-conditional diffusion without table ordering, outperforming autoregressive baselines on multi-hop correlations and single-table fidelity across six real RDBs.
-
Continuous-Time Analysis for Minimax and Bilevel Problems
Introduces a modular unified Lyapunov template for continuous-time analysis of minimax, bilevel (via penalty), and min-min-max problems with explicit time-scale thresholds.
-
When and Why Adversarial Training Improves PINNs: A Neural Tangent Kernel Perspective
Adversarial training improves PINNs by using the discriminator to mitigate spectral bias and stiffness, with a new NTK-based framework providing theoretical grounding and a practical algorithm.
-
RaPD: Resolution-Agnostic Pixel Diffusion via Semantics-Enriched Implicit Representations
RaPD enables resolution-agnostic image generation by diffusing in a semantics-enriched continuous Neural Image Field latent space using semantic guidance and a coordinate-queried attention renderer.
-
Intermediate Representations are Strong AI-Generated Image Detectors
Intermediate layer embedding sensitivity to perturbations distinguishes AI-generated images from real ones, yielding higher AUROC on GenImage and Forensics Small benchmarks than prior methods.
-
Efficient Diffusion Distillation via Embedding Loss
Embedding Loss aligns feature distributions via MMD in random network embeddings to boost one-step diffusion distillation, reaching SOTA FID of 1.475 on CIFAR-10 unconditional generation.
-
Energy-Guided Generative Modeling for Low-Energy Molecular Structure Discovery
EnFlow integrates flow-based conformer generation with energy landscape modeling to enable joint ensemble generation and ground-state identification using only 1-2 ODE steps.
-
RefTon: Reference person shot assist virtual Try-on
RefTon is a flux-based virtual try-on method that uses unpaired reference images of the target garment on different people to guide texture and detail preservation in a streamlined person-to-person pipeline without body parsing or masks.
-
Accelerating Redshift-Conditioned Galaxy Image Synthesis with One-step Generative Modeling
One-step pixel-MeanFlow models recover key galaxy morphology statistics at orders-of-magnitude lower computational cost than standard DDPM sampling while remaining weaker on fine-grained structure.