Consistency models achieve fast one-step generation with SOTA FID of 3.55 on CIFAR-10 and 6.20 on ImageNet 64x64 by directly mapping noise to data, outperforming prior distillation techniques.
hub Canonical reference
Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 step s
Canonical reference. 80% of citing Pith papers cite this work as background.
25
Pith papers citing it
Background
80% of classified citations
hub tools
citation-role summary
background 4
baseline 1
citation-polarity summary
representative citing papers
Rectified flow learns straight-path neural ODEs for distribution transport, yielding efficient generative models and domain transfers that work well even with a single simulation step.
Introduces a Bridge latent interface that maps mismatched student latents into teacher space, enabling distillation from modern diffusion teachers to compact one-step students and raising SD 1.5 HPSv3 from 5.4 to 9.4 while keeping one-step speed.
Develops primal-dual inference (PDI) that jointly infers optimal primal distributions and dual multipliers during diffusion sampling using a dual-conditioned score network.
CF-VLA uses a coarse initialization over endpoint velocity followed by single-step refinement to achieve strong performance with low inference steps on CALVIN, LIBERO, and real-robot tasks.
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.
Early and late denoising steps in masked diffusion LMs are robust to smaller-model replacement, enabling 17% FLOPs reduction with modest generative quality loss.
Diff-ANO uses conditional consistency models and adjoint neural operator surrogates to enable fast, high-quality USCT reconstructions under sparse and partial views by replacing slow PDE solvers and enabling few-step sampling.
D-Garment is a template-specific latent diffusion model that generates dynamic 3D garment deformations conditioned on body shape, motion, and physical material properties using training data from a physics-based simulator.
Latent Consistency Models enable high-fidelity text-to-image generation in 2-4 steps by directly predicting solutions to the probability flow ODE in latent space, distilled from pre-trained LDMs.
Diffusion models solve noisy (non)linear inverse problems via approximated posterior sampling that blends diffusion steps with manifold gradients without strict consistency projection.
Diffusion-QL uses conditional diffusion models as expressive policies in offline RL by coupling behavior cloning with Q-value maximization, achieving SOTA on most D4RL tasks.
TISED decomposes inference optimization effects on embodied tasks and identifies paradoxical outcomes where faster per-step inference can increase task completion time on static tasks or raise success rates on dynamic tasks.
PPM derives a tractable gradient for exact KL optimization in diffusion variational inversion to achieve unbiased posterior matching without heuristic approximations.
REPA-P aligns intermediate representations in diffusion models with physical states using first-principles PDE residuals to accelerate convergence and boost out-of-distribution robustness on PDE tasks.
MetaSR adaptively orchestrates metadata in a DiT-based generative SR model to deliver up to 1 dB PSNR gains and 50% bitrate savings across diverse content and degradations.
DOLLAR combines variational score and consistency distillation for few-step video generation plus latent reward optimization, reporting 82.57 VBench score and up to 278x speedup over the teacher diffusion model for 128-frame 10-second videos.
Moment-matched GMM kernels in DDIM yield lower FID and higher IS than Gaussian kernels at small sampling steps on CelebA-HQ, FFHQ, ImageNet, and Stable Diffusion tasks.
Causal probing of attention in audio separation transformers identifies dual pathways and asynchronous convergence, enabling a training-free Layer-Selective Attention Caching method that reduces self-attention computation by ~25% with negligible quality loss.
Lens is a 3.8B-parameter text-to-image model that reaches competitive or superior performance to >6B-parameter systems using 19.3% of the training compute of Z-Image through a densely captioned 800M dataset, multi-resolution batching, semantic VAE, strong language encoder, RL fine-tuning, and 4-step
A consistency-regularized Euclidean-Wasserstein-2 gradient flow performs joint posterior sampling and prompt optimization in latent space for efficient low-NFE inverse problem solving with diffusion models.
AdaCorrection adaptively corrects offset caches in DiT inference via on-the-fly spatio-temporal validity checks to maintain near-original FID with moderate acceleration.
Cross-fluctuations detect discrete phase transitions during diffusion sampling trajectories, yielding efficiency gains in generation and zero-shot tasks.
The paper proposes CDCD, a continuous-time and continuous-space diffusion framework for categorical data, and reports results on language modeling tasks.
citing papers explorer
No citing papers match the current filters.