Pith. sign in

REVIEW 27 cited by

Flow Matching in Latent Space

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

arxiv 2307.08698 v1 pith:DT4W3ZIT submitted 2023-07-17 cs.CV cs.LG

Flow Matching in Latent Space

classification cs.CV cs.LG
keywords flowmatchinglatentgenerationimagecomputationaldistributiongenerative
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Flow matching is a recent framework to train generative models that exhibits impressive empirical performance while being relatively easier to train compared with diffusion-based models. Despite its advantageous properties, prior methods still face the challenges of expensive computing and a large number of function evaluations of off-the-shelf solvers in the pixel space. Furthermore, although latent-based generative methods have shown great success in recent years, this particular model type remains underexplored in this area. In this work, we propose to apply flow matching in the latent spaces of pretrained autoencoders, which offers improved computational efficiency and scalability for high-resolution image synthesis. This enables flow-matching training on constrained computational resources while maintaining their quality and flexibility. Additionally, our work stands as a pioneering contribution in the integration of various conditions into flow matching for conditional generation tasks, including label-conditioned image generation, image inpainting, and semantic-to-image generation. Through extensive experiments, our approach demonstrates its effectiveness in both quantitative and qualitative results on various datasets, such as CelebA-HQ, FFHQ, LSUN Church & Bedroom, and ImageNet. We also provide a theoretical control of the Wasserstein-2 distance between the reconstructed latent flow distribution and true data distribution, showing it is upper-bounded by the latent flow matching objective. Our code will be available at https://github.com/VinAIResearch/LFM.git.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 27 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Flow-Map GRPO: Reinforcement Learning for Few-Step Flow-Map Generators via Anchored Stochastic Composition

    cs.LG 2026-07 unverdicted novelty 7.0

    Flow-Map GRPO uses anchored stochastic flow map composition to enable GRPO-based RL alignment of deterministic few-step flow-map generators while preserving their marginal paths.

  2. Beyond Trajectory Matching: Reflow with Marginal Distribution Alignment

    cs.LG 2026-06 unverdicted novelty 7.0

    Introduces a marginal-alignment regularizer for reflow distillation of diffusion models that aligns endpoint marginals, supported by a telescoping TV bound and benchmark experiments.

  3. MATCH: Flow Matching for Multi-View Anomaly Detection

    cs.CV 2026-06 unverdicted novelty 7.0

    MATCH is the first flow matching method for multi-view anomaly detection, reporting SOTA results on Real-IAD and the first comprehensive evaluation on MANTA-Tiny while enabling real-time use by omitting the divergence term.

  4. Balancing Image Compression and Generation with Bootstrapped Tokenization

    cs.LG 2026-06 unverdicted novelty 7.0

    SelfBootTok decomposes image tokens into global and local groups via self-bootstrapped learning, enabling generators to use only global tokens for ~40% less computation and a new SOTA gFID of 1.56 with 64 tokens.

  5. Constraint-Aware Flow Matching: Decision Aligned End-to-End Training for Constrained Sampling

    cs.LG 2026-05 unverdicted novelty 7.0

    Constraint-Aware Flow Matching integrates constraint projections into the flow matching training objective to align model dynamics with constrained sampling and reduce distributional shift.

  6. Generative Modeling of Discrete Data Using Geometric Latent Subspaces

    stat.ML 2026-01 unverdicted novelty 7.0

    A geometric latent-subspace model on Riemannian manifolds of categorical distributions enables low-dimensional generative modeling of discrete data via isometries and geometric PCA for flow matching.

  7. Privacy Attacks on Image AutoRegressive Models

    cs.CV 2025-02 unverdicted novelty 7.0

    Image autoregressive models leak substantially more training data than diffusion models under membership inference, dataset inference with as few as 4 samples, and data extraction attacks.

  8. DanceOPD: On-Policy Generative Field Distillation

    cs.CV 2026-06 conditional novelty 6.0

    Hard-routed, single low-noise on-policy velocity matching composes conflicting image-generation capabilities into one flow student better than joint training, merging, or dense OPD baselines.

  9. Pareto-Enhanced Portrait Generation: Vision-Aligned Text Supervision for Alignment, Realism, and Aesthetics

    cs.CV 2026-05 unverdicted novelty 6.0

    A feature supervision approach using SigLIP 2 extracts multi-granularity vision-aligned text representations to supervise MM-DiT image branches, pushing the Pareto frontier for portrait generation across alignment, re...

  10. Beyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives

    cs.RO 2026-05 unverdicted novelty 6.0

    BeyondDrive augments imitation learning with synthesized safety-critical negative trajectories and a repulsive loss to improve safety in autonomous driving, reporting 89.7 PDMS on NAVSIMv1 and generalization to other models.

  11. Wavelet Flow Matching for Multi-Scale Physics Emulation

    cs.LG 2026-05 unverdicted novelty 6.0

    Wavelet Flow Matching emulates multi-scale PDE-governed systems by transporting velocities directly in a hierarchical wavelet representation via U-Net, yielding improved long-horizon stability and spectral accuracy on...

  12. Inference-Time Attribute Distribution Alignment for Unconditional Diffusion

    cs.LG 2026-05 unverdicted novelty 6.0

    An optimal control formulation adds time-dependent perturbations to the reverse diffusion process to match target attribute distributions while preserving sample fidelity.

  13. Flow Matching with Arbitrary Auxiliary Paths

    cs.LG 2026-05 unverdicted novelty 6.0

    AuxPath-FM extends flow matching to arbitrary auxiliary distributions while preserving the continuity equation and marginal training objective.

  14. P-Guide: Parameter-Efficient Prior Steering for Single-Pass CFG Inference

    cs.AI 2026-05 unverdicted novelty 6.0

    P-Guide achieves single-pass classifier-free guidance in flow matching by modulating the initial latent state and is equivalent to standard CFG under a first-order approximation while cutting latency by half.

  15. A Few-Step Generative Model on Cumulative Flow Maps

    cs.LG 2026-05 unverdicted novelty 6.0

    Cumulative flow maps unify few-step generative modeling for diffusion and flow models via cumulative transport and parameterization with minimal changes to time embeddings and objectives.

  16. Bi-Lipschitz Autoencoder With Injectivity Guarantee

    cs.LG 2026-04 conditional novelty 6.0

    BLAE adds injective regularization via a separation criterion and bi-Lipschitz constraints to guarantee injectivity and geometric preservation in autoencoders, outperforming prior methods on manifold fidelity under sp...

  17. Training-Free Image Editing with Visual Context Integration and Concept Alignment

    cs.CV 2026-04 unverdicted novelty 6.0

    VicoEdit performs training-free image editing by transforming source images directly with visual context and concept-alignment-guided posterior sampling, outperforming training-based methods.

  18. MPDiT: Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion Model

    cs.CV 2026-03 unverdicted novelty 6.0

    MPDiT uses a hierarchical multi-patch design in transformers to lower computation in diffusion models by handling coarse global features first then fine local details, plus faster-converging embeddings.

  19. Contrast-X: A Multi-Modal Contrast Image Synthesis Benchmark and Universal Modality Flow Matching

    cs.CV 2026-01 unverdicted novelty 6.0

    Contrast-X benchmark and FlowMI model enable synthesis of contrast-enhanced images from arbitrary non-contrast modality inputs using multi-modal flow matching.

  20. Latent Stochastic Interpolants

    cs.LG 2025-06 unverdicted novelty 6.0

    Latent Stochastic Interpolants jointly optimize encoder-decoder and a latent-space stochastic interpolant using a continuous-time ELBO to transform arbitrary priors into aggregated posteriors.

  21. EventFlow: Forecasting Temporal Point Processes with Flow Matching

    cs.LG 2024-10 unverdicted novelty 6.0

    EventFlow applies flow matching to learn joint distributions over event times for temporal point processes, reporting 20-53% lower forecast error than autoregressive baselines on standard TPP benchmarks with fewer sam...

  22. Spectral Consistent Flow for One-step 3D Medical Image Translation

    cs.CV 2026-07 conditional novelty 5.0

    A one-step latent Brownian-bridge flow plus frequency-domain gain correction produces more accurate 3D medical image translations than multi-step diffusion and prior single-step baselines across four datasets.

  23. Straight-Path Flow Matching for Incomplete Multi-View Clustering

    cs.CV 2026-07 conditional novelty 5.0

    Straight-path flow matching between paired latent representations outperforms diffusion-based methods for incomplete multi-view clustering by preserving cluster structure during view completion.

  24. DanceOPD: On-Policy Generative Field Distillation

    cs.CV 2026-06 unverdicted novelty 5.0

    DanceOPD routes samples across capability velocity fields in flow-matching models and trains via on-policy student-induced states to compose T2I, local editing, and global editing without mutual interference.

  25. Autoregression-Free Neural Operators for Time-Dependent PDEs

    cs.LG 2026-05 unverdicted novelty 5.0

    AFNO learns continuous-time dynamics in latent space via flow matching for time-dependent PDEs to reduce error accumulation in long-horizon forecasts.

  26. Physics Priors Offer Useful Accuracy-Carbon Trade-Offs in Spatio-Temporal Forecasting

    cs.LG 2025-09 unverdicted novelty 5.0

    Stronger physics priors in neural networks for spatio-temporal shear flow forecasting yield substantially lower training carbon footprints than weak or no priors, though inference savings are less consistent.

  27. FlowDec: Temporal Conditional Flow Decorruptor for Robust Continuous Vision-Language Navigation

    cs.CV 2026-06 unverdicted novelty 4.0

    FlowDec is a novel image restoration framework using hybrid temporal conditioning and action-centroid filtering that claims to outperform prior decorruption methods on navigation accuracy and latency in VLN-CE.