Cross-attention maps serve as a tractable surrogate for manifold proximity, enabling automatic synthesis of anchors that suppress normal-space drift in diffusion unlearning.
Cambridge university press
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
TAB-DRW embeds detectable watermarks in the frequency domain of normalized synthetic tabular data via DFT and rank-based pseudorandom bits, achieving robustness to attacks while preserving fidelity and supporting mixed data types.
PACE recovers geometry-consistent continuous transport dynamics from destructive single-cell snapshots via anisotropic metrics and neural bridges, reducing reconstruction distances by 23.7% on average across seven datasets.
An online conformal prediction framework for non-exchangeable panel data that forms prediction sets using related units' contemporaneous data with adaptive similarity weights and miscoverage levels to deliver stepwise and long-run coverage guarantees.
Projecting VAE latents to a fixed spherical radius and replacing linear interpolation with spherical linear interpolation improves class-conditional ImageNet-256 FID while leaving the diffusion architecture unchanged.
P-Flow solves linear inverse problems by optimizing the flow's source latent with a proxy gradient and a Gaussian-sphere projection, matching or beating prior restoration methods at far lower cost.
A unified spectral condition for μP under width-depth scaling reveals a transition at k=1 vs k≥2 transformations per residual block and enables stable feature learning for practical architectures like Transformers.
A new kernel nonconformity score for multivariate conformal prediction that adapts to residual geometry, provides finite-sample coverage, and achieves convergence rates based on effective kernel rank rather than ambient dimension.
citing papers explorer
-
AutoAnchor: Stable Diffusion Unlearning Using Cross-Attention as a Manifold Surrogate
Cross-attention maps serve as a tractable surrogate for manifold proximity, enabling automatic synthesis of anchors that suppress normal-space drift in diffusion unlearning.
-
Robust Spectral Watermark for Synthetic Tabular Data
TAB-DRW embeds detectable watermarks in the frequency domain of normalized synthetic tabular data via DFT and rank-based pseudorandom bits, achieving robustness to attacks while preserving fidelity and supporting mixed data types.
-
PACE: Geometry-Aware Bridge Transport for Single-Cell Trajectory Inference
PACE recovers geometry-consistent continuous transport dynamics from destructive single-cell snapshots via anisotropic metrics and neural bridges, reducing reconstruction distances by 23.7% on average across seven datasets.
-
Online Conformal Prediction for Non-Exchangeable Panel Data
An online conformal prediction framework for non-exchangeable panel data that forms prediction sets using related units' contemporaneous data with adaptive similarity weights and miscoverage levels to deliver stepwise and long-run coverage guarantees.
-
Aligning Latent Geometry for Spherical Flow Matching in Image Generation
Projecting VAE latents to a fixed spherical radius and replacing linear interpolation with spherical linear interpolation improves class-conditional ImageNet-256 FID while leaving the diffusion architecture unchanged.
-
P-Flow: Proxy-gradient Flows for Linear Inverse Problems
P-Flow solves linear inverse problems by optimizing the flow's source latent with a proxy gradient and a Gaussian-sphere projection, matching or beating prior restoration methods at far lower cost.
-
Spectral Condition for $\mu$P under Width-Depth Scaling
A unified spectral condition for μP under width-depth scaling reveals a transition at k=1 vs k≥2 transformations per residual block and enables stable feature learning for practical architectures like Transformers.
-
A Kernel Nonconformity Score for Multivariate Conformal Prediction
A new kernel nonconformity score for multivariate conformal prediction that adapts to residual geometry, provides finite-sample coverage, and achieves convergence rates based on effective kernel rank rather than ambient dimension.