CSGuard binds diffusion-model watermarks to a secret matrix via compressed sensing, cutting forgery attack success from 100% to 28.12% while preserving 100% detection on legitimate images.
Diffusion models: A comprehensive survey of methods and applications
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 8roles
background 1polarities
background 1representative citing papers
MIC casts diffusion motion generation as stochastic control to support both objective-based and criterion-based constraints without training or differentiability requirements.
A simulation-based inference method with Gaussian process emulators trained on 1300 kilonova simulations recovers parameters accurately and rapidly while avoiding MCMC biases from likelihood misspecification.
PG-3DGS couples 3D Gaussian Splatting with differentiable physics so that optimized shapes satisfy both visual fidelity and physical objectives such as pouring and aerodynamic lift, with real-world 3D-printed validation.
Generative models learn rules before memorizing data, creating an innovation window whose width depends on dataset size and rule complexity, observed in both diffusion and autoregressive architectures.
CDiT uses a diffusion transformer conditioned on position to generate high-fidelity THz channels in sparse beamspace under the hybrid planar-spherical wave model, outperforming benchmarks on realistic datasets.
MIRAGE combines a medical CLIP model, a diffusion generator, and an LLM into an accessible interface for retrieving and creating educational medical images and texts.
citing papers explorer
-
CSGuard: Toward Forgery-Resistant Watermarking in Diffusion Models via Compressed Sensing Constraint
CSGuard binds diffusion-model watermarks to a secret matrix via compressed sensing, cutting forgery attack success from 100% to 28.12% while preserving 100% detection on legitimate images.
-
Training-free Controllable Human Motion Generation under Heterogeneous Constraints
MIC casts diffusion motion generation as stochastic control to support both objective-based and criterion-based constraints without training or differentiability requirements.
-
Rapid and robust simulation-based inference for kilonovae
A simulation-based inference method with Gaussian process emulators trained on 1300 kilonova simulations recovers parameters accurately and rapidly while avoiding MCMC biases from likelihood misspecification.
-
PG-3DGS: Optimizing 3D Gaussian Splatting to Satisfy Physics Objectives
PG-3DGS couples 3D Gaussian Splatting with differentiable physics so that optimized shapes satisfy both visual fidelity and physical objectives such as pouring and aerodynamic lift, with real-world 3D-printed validation.
-
The two clocks and the innovation window: When and how generative models learn rules
Generative models learn rules before memorizing data, creating an innovation window whose width depends on dataset size and rule complexity, observed in both diffusion and autoregressive architectures.
-
CDiT: Conditional Diffusion Transformer for Geometry-Aware Terahertz Cross Far- and Near-Field Channel Generation
CDiT uses a diffusion transformer conditioned on position to generate high-fidelity THz channels in sparse beamspace under the hybrid planar-spherical wave model, outperforming benchmarks on realistic datasets.
-
MIRAGE: Retrieval and Generation of Multimodal Images and Texts for Medical Education
MIRAGE combines a medical CLIP model, a diffusion generator, and an LLM into an accessible interface for retrieving and creating educational medical images and texts.
- PECKER: A Precisely Efficient Critical Knowledge Erasure Recipe For Machine Unlearning in Diffusion Models