REVIEW 11 cited by
Inductive Moment Matching
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Diffusion models and Flow Matching generate high-quality samples but are slow at inference, and distilling them into few-step models often leads to instability and extensive tuning. To resolve these trade-offs, we propose Inductive Moment Matching (IMM), a new class of generative models for one- or few-step sampling with a single-stage training procedure. Unlike distillation, IMM does not require pre-training initialization and optimization of two networks; and unlike Consistency Models, IMM guarantees distribution-level convergence and remains stable under various hyperparameters and standard model architectures. IMM surpasses diffusion models on ImageNet-256x256 with 1.99 FID using only 8 inference steps and achieves state-of-the-art 2-step FID of 1.98 on CIFAR-10 for a model trained from scratch.
Forward citations
Cited by 11 Pith papers
-
DriftXpress: Faster Drifting Models via Projected RKHS Fields
DriftXpress approximates the attraction field of drifting models with a Nyström landmark projection, reducing training time by 2.6–6.7× at comparable FID.
-
Understanding LoRA as Knowledge Memory: An Empirical Analysis
LoRA modules function as composable knowledge memories for LLMs with measurable storage capacity, internalization efficiency, and advantages in multi-module long-context reasoning.
-
Amortized Moment Matching for Visual Generation
Amortized Fréchet Distance uses neural nets to match conditional means and covariances, yielding stronger one-step visual generators than explicit FD-loss or multi-step teachers.
-
Flow Map Learning via Nongradient Vector Flow
SGFlow learns the integral map of a probability-flow ODE via a stop-gradient loss whose only stationary point is the true flow map, and it reaches the best-in-comparison FID at 10 steps on CIFAR-10.
-
Parallel Decoding Distillation for Fast Image and Video Generation
A trajectory-based distillation method trains a student to predict multiple mean velocities per network evaluation, enabling 4-8 step generation with competitive quality and improved diversity.
-
Autoregressive One-Step Generative Modeling for Dynamical System Forecasting
MeLISA extends pixel-space MeanFlow to one-step window-conditioned autoregressive forecasting, improving long-horizon turbulence statistics over neural-operator baselines.
-
MENO: MeanFlow-Enhanced Neural Operators for Dynamical Systems
MENO restores multi-scale structure in neural-operator PDE surrogates via one-step improved MeanFlow, claiming up to 2× better power-spectrum accuracy and up to 14× faster inference than DDIM enhancement.
-
Dual-End Consistency Model
DE-CM trains a flow-map consistency model on three sub-trajectories (coupling, instantaneous, noise-to-noisy) and reports 1.70 FID one-step on ImageNet 256.
-
Scalable GANs with Transformers
A transformer-only GAN trained in VAE latent space with multi-level noise supervision and width-scaled learning rates achieves FID 2.96 on ImageNet-256 in 40 epochs.
-
Transition Models: Rethinking the Generative Learning Objective
TiM trains a single diffusion-type model on arbitrary time-interval transitions, achieving strong one-step and multi-step text-to-image generation with 865M parameters.
-
Diffuse and Disperse: Image Generation with Representation Regularization
Adding a dispersion regularizer to intermediate features of diffusion and flow models consistently improves FID on ImageNet and one-step generation, with no additional parameters, pretraining, or external data.
Discussion (0). Continue with ORCID to comment.