Z²-Sampling implicitly realizes zero-cost zigzag trajectories for curvature-aware semantic alignment in diffusion models by reducing multi-step paths via operator dualities and temporal caching while synthesizing a directional derivative penalty.
Text-to-image rectified flow as plug-and-play priors
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 3years
2026 3roles
background 1polarities
background 1representative citing papers
A training-free two-stage pipeline uses cross-space dual-branch denoising with CLIP-guided voxel alignment and SDF blending for geometry, followed by view-conditioned 2D diffusion texture projection, to produce dual-semantic 3D illusions in 3-5 minutes.
VAGS adapts the CFG scale at each ODE step using velocity alignment signals to raise structural fidelity in editing and sample quality in generation over fixed-scale baselines.
citing papers explorer
-
$Z^2$-Sampling: Zero-Cost Zigzag Trajectories for Semantic Alignment in Diffusion Models
Z²-Sampling implicitly realizes zero-cost zigzag trajectories for curvature-aware semantic alignment in diffusion models by reducing multi-step paths via operator dualities and temporal caching while synthesizing a directional derivative penalty.
-
JanusMesh: Fast and Zero-Shot 3D Visual Illusion Generation via Cross-Space Denoising
A training-free two-stage pipeline uses cross-space dual-branch denoising with CLIP-guided voxel alignment and SDF blending for geometry, followed by view-conditioned 2D diffusion texture projection, to produce dual-semantic 3D illusions in 3-5 minutes.
-
VAGS: Velocity Adaptive Guidance Scale for Image Editing and Generation
VAGS adapts the CFG scale at each ODE step using velocity alignment signals to raise structural fidelity in editing and sample quality in generation over fixed-scale baselines.