REVIEW 16 cited by
Flow map matching with stochastic interpolants: A mathematical framework for consistency models
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
Generative models based on dynamical equations such as flows and diffusions offer exceptional sample quality, but require computationally expensive numerical integration during inference. The advent of consistency models has enabled efficient one-step or few-step generation, yet despite their practical success, a systematic understanding of their design has been hindered by the lack of a comprehensive theoretical framework. Here we introduce Flow Map Matching (FMM), a principled framework for learning the two-time flow map of an underlying dynamical generative model, thereby providing this missing mathematical foundation. Leveraging stochastic interpolants, we propose training objectives both for distillation from a pre-trained velocity field and for direct training of a flow map over an interpolant or a forward diffusion process. Theoretically, we show that FMM unifies and extends a broad class of existing approaches for fast sampling, including consistency models, consistency trajectory models, and progressive distillation. Experiments on CIFAR-10 and ImageNet-32 highlight that our approach can achieve sample quality comparable to flow matching while reducing generation time by a factor of 10-20.
Forward citations
Cited by 16 Pith papers
-
Beckmann Transport Models: From Autonomous Flows to One-Step Maps
An autonomous (time-independent) flow-matching drift that obeys a simple divergence equation exactly transports samples to singular targets, yielding a corrected Equilibrium Matching loss and a one-step map.
-
Hacking Generative Perplexity: Why Unconditional Text Evaluation Needs Distributional Metrics
Zero-parameter naive samplers achieve state-of-the-art generative perplexity while producing incoherent text, proving the metric is unsound; distributional divergences like MAUVE and energy distance correctly rank the...
-
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.
-
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.
-
Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation
Self-consistent distribution matching plus cache-aware mixed-step training improves 2–4 NFE video quality on Wan 2.1 and real-time autoregressive backbones without extra inference cost.
-
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.
-
Transition Matching Distillation for Fast Video Generation
Splitting a video diffusion model into a fixed feature extractor and a small recurrent flow head lets TMD generate videos in one to two effective steps with better VBench scores than prior distilled models.
-
DASIP: Dynamic Test-Time Compute Scaling for Robot Control with Stochastic Interpolant Policies
A difficulty classifier adaptively selects step count, solver, and ODE/SDE mode for stochastic-interpolant robot policies, reporting 2.6–4.4x compute savings with roughly unchanged success rates.
-
Understanding, Accelerating, and Improving MeanFlow Training
Training MeanFlow by first forming instantaneous velocity and short-gap average velocity, then shifting to long gaps, improves 1-NFE ImageNet FID from 3.43 to 2.87 and speeds training by about 2.5x.
-
Populate-A-Scene: Affordance-Aware Human Video Generation
A fine-tuned text-to-video model inserts a person into a scene and generates an interaction video without bounding boxes or pose input, and its attention maps reveal a latent sense of affordance.
-
FlowCTS: On-policy Continuous Trajectory Supervision of Flow Models
Trajectory-derived, temporally weighted velocity matching from shared student states outperforms KL-based on-policy distillation for multi-reference flow model post-training.
-
Layer-Parallel Inference Reduces Encrypted Nonlinear Depth in Transformers
SNLP reduces symbolic FHE bootstraps from 53 to 20 on a 0.5B model with +1.2% PPL degradation and lower polynomial-error amplification than sequential inference.
-
Solving Inverse Problems via Diffusion-Based Priors: An Approximation-Free Ensemble Sampling Approach
A weighted-particle sampler evolves the posterior through the diffusion model's reverse dynamics, with theoretical error bounds and improved image reconstructions.
-
The Principles of Diffusion Models
A principled monograph showing that variational, score-based, and flow-based diffusion models are instances of one continuous-time transport backbone, with sampling equal to solving a differential equation governed by...
Discussion (0). Sign in to comment.