FTM learns the probability current velocity from trajectories to deliver fast, trajectory-aware ensemble predictions for stochastic dynamical systems and PDEs.
hub
Inductive moment matching
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Midpoint Generative Models define a midpoint divergence from flow matching symmetry and derive its variational form as a tractable objective for training competitive one-step generators.
NanoGen unifies DiT training on ImageNet and T2I, reveals negative Pearson correlations (-0.377 to -0.580) in method rankings across metrics from 21 models, and motivates DiffusionBench for holistic evaluation.
RTM uses iterative refinement of latent codes in generative models to improve both precision and recall alongside competitive FID scores on CIFAR-10, CelebA-HQ, and few-shot datasets.
W-Flow compresses a Wasserstein gradient flow defined via Sinkhorn divergence into a single-step neural generator, reporting 1.29 FID on ImageNet 256x256 with improved mode coverage.
OT-NFM parameterizes the flow map directly with neural flows and uses optimal transport for consistent noise-data couplings to achieve ODE-free one-step generation while avoiding mean collapse.
LoRA modules are a complementary, finite-capacity parametric memory for LLMs: capacity grows with rank, small ranks are most parameter-efficient, synthetic QA data helps most, and practical multi-LoRA systems are bottlenecked by routing and merging degradation.
MeanFlow uses a derived identity between average and instantaneous velocities to train one-step flow models, achieving FID 3.43 on ImageNet 256x256 with 1-NFE from scratch.
DriftXpress approximates the attraction field of drifting models with a Nyström landmark projection, reducing training time by 2.6–6.7× at comparable FID.
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.
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.
Stabilizes MeanFlow for large-scale diffusion distillation via discrete warm-up and trajectory alignment, reporting better results on FLUX.1-dev and HunyuanImage 3.0.
One-step pixel-MeanFlow models recover key galaxy morphology statistics at orders-of-magnitude lower computational cost than standard DDPM sampling while remaining weaker on fine-grained structure.
citing papers explorer
-
First-Order Trajectory Matching: Fast Ensemble Predictions of Chaotic, Turbulent, Stochastic Systems
FTM learns the probability current velocity from trajectories to deliver fast, trajectory-aware ensemble predictions for stochastic dynamical systems and PDEs.
-
Midpoint Generative Models
Midpoint Generative Models define a midpoint divergence from flow matching symmetry and derive its variational form as a tractable objective for training competitive one-step generators.
-
DiffusionBench: On Holistic Evaluation of Diffusion Transformers
NanoGen unifies DiT training on ImageNet and T2I, reveals negative Pearson correlations (-0.377 to -0.580) in method rankings across metrics from 21 models, and motivates DiffusionBench for holistic evaluation.
-
One Pass Is Not Enough: Recursive Latent Refinement for Generative Models
RTM uses iterative refinement of latent codes in generative models to improve both precision and recall alongside competitive FID scores on CIFAR-10, CelebA-HQ, and few-shot datasets.
-
One-Step Generative Modeling via Wasserstein Gradient Flows
W-Flow compresses a Wasserstein gradient flow defined via Sinkhorn divergence into a single-step neural generator, reporting 1.29 FID on ImageNet 256x256 with improved mode coverage.
-
ODE-free Neural Flow Matching for One-Step Generative Modeling
OT-NFM parameterizes the flow map directly with neural flows and uses optimal transport for consistent noise-data couplings to achieve ODE-free one-step generation while avoiding mean collapse.
-
Understanding LoRA as Knowledge Memory: An Empirical Analysis
LoRA modules are a complementary, finite-capacity parametric memory for LLMs: capacity grows with rank, small ranks are most parameter-efficient, synthetic QA data helps most, and practical multi-LoRA systems are bottlenecked by routing and merging degradation.
-
Mean Flows for One-step Generative Modeling
MeanFlow uses a derived identity between average and instantaneous velocities to train one-step flow models, achieving FID 3.43 on ImageNet 256x256 with 1-NFE from scratch.
-
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.
-
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.
-
Stabilizing, Scaling & Enhancing MeanFlow for Large-scale Diffusion Distillation
Stabilizes MeanFlow for large-scale diffusion distillation via discrete warm-up and trajectory alignment, reporting better results on FLUX.1-dev and HunyuanImage 3.0.
-
Accelerating Redshift-Conditioned Galaxy Image Synthesis with One-step Generative Modeling
One-step pixel-MeanFlow models recover key galaxy morphology statistics at orders-of-magnitude lower computational cost than standard DDPM sampling while remaining weaker on fine-grained structure.