Discrete Flow Maps

• URL: http://arxiv.org/abs/2604.09784v2
• Date: Tue, 14 Apr 2026 17:35:15 GMT
• Title: Discrete Flow Maps
• Abstract summary: Flow Maps compress generative trajectories into single-step mappings.<n>Standard formulations rely on Euclidean regression losses geometrically ill-suited for discrete data.<n>We recast standard flow map training for the discrete domain, aligning the training dynamics with the discrete nature of language.
• Score: 19.374556402778207
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The sequential nature of autoregressive next-token prediction imposes a fundamental speed limit on large language models. While continuous flow models offer a path to parallel generation, they traditionally demand expensive iterative integration. Flow Maps bypass this bottleneck by compressing generative trajectories into single-step mappings, theoretically enabling the generation of full text sequences from noise in a single forward pass. However, standard formulations rely on Euclidean regression losses that are geometrically ill-suited for discrete data. In this work, we resolve this conflict with Discrete Flow Maps, a framework that reconciles trajectory compression with the geometry of the probability simplex. We recast standard flow map training for the discrete domain, aligning the training dynamics with the discrete nature of language. Empirically, this strict geometric alignment allows our method to surpass previous state-of-the-art results in discrete flow modeling.

Related papers

• Beckmann Transport Models: From Autonomous Flows to One-Step Maps [47.88178310873025]
  We propose an instantiation of flow matching that relies on a time-independent velocity field to map between two distributions.<n>We also show that the one-step generative map associated with this flow is the unique solution of a simple conservation equation.
  arXiv  Detail & Related papers  (2026-08-03T04:45:52Z)
• PolyFlow: Continuous Topology Embedding Flow Matching for Artist-style Mesh Generation [31.59262139357425]
  Autoregressive Transformers dominate high-quality mesh generation by producing artist-worthy topologies.<n>While continuous diffusion and flow-matching methods support efficient parallel synthesis, they cannot be directly applied to meshes.<n>We introduce a compact topology embedder that projects discrete mesh positions and normals into continuous per-vertex embeddings.<n>After pretraining and freezing this embedder, any raw mesh can be fully converted into a continuous per-vertex state space unifying position, normal, and implicit topological attributes.
  arXiv  Detail & Related papers  (2026-06-25T18:29:06Z)
• Unrestrained Simplex Denoising for Discrete Data. A Non-Markovian Approach Applied to Graph Generation [50.328122325596865]
  We introduce simplex denoising, a simple yet effective generative framework that operates on the probability simplex.<n>For a given clean data point, noisy representations at different times are conditionally independent.<n> Empirically, emphunrestrained simplex denoising surpasses strong discrete diffusion and flow-matching baselines.
  arXiv  Detail & Related papers  (2026-03-30T15:26:56Z)
• Categorical Flow Maps [42.309126712129384]
  Categorical Flow Maps is a flow-matching method for accelerated few-step generation of categorical data via self-distillation.<n>We achieve state-of-the-art few-step results on images, molecular graphs, and text, with strong performance even in single-step generation.
  arXiv  Detail & Related papers  (2026-02-12T18:10:46Z)
• PRISM: Parallel Residual Iterative Sequence Model [52.26239951489612]
  We propose PRISM (Parallel Residual Iterative Sequence Model) to resolve this tension.<n>PRISM introduces a solver-inspired inductive bias that captures key structural properties of multi-step refinement in a parallelizable form.<n>We prove that this formulation achieves Rank-$L$ accumulation, structurally expanding the update manifold beyond the single-step Rank-$1$ bottleneck.
  arXiv  Detail & Related papers  (2026-02-11T12:39:41Z)
• FlowConsist: Make Your Flow Consistent with Real Trajectory [99.22869983378062]
  We argue that current fast-flow training paradigms suffer from two fundamental issues.<n> conditional velocities constructed from randomly paired noise-data samples introduce systematic trajectory drift.<n>We propose FlowConsist, a training framework designed to enforce trajectory consistency in fast flows.
  arXiv  Detail & Related papers  (2026-02-06T03:24:23Z)
• ProFlow: Zero-Shot Physics-Consistent Sampling via Proximal Flow Guidance [35.08166384258028]
  ProFlow is a framework for zero-shot physics-consistent sampling.<n>It reconciles strict physical consistency and observational fidelity with the statistical structure of the pre-trained prior.<n>It achieves superior physical and observational consistency, as well as more accurate distributional statistics.
  arXiv  Detail & Related papers  (2026-01-28T03:57:00Z)
• FlowPath: Learning Data-Driven Manifolds with Invertible Flows for Robust Irregularly-sampled Time Series Classification [14.643457217551484]
  We propose FlowPath, a novel approach that learns the geometry of the control path via an invertible neural flow.<n>We show that FlowPath consistently achieves statistically significant improvements in classification accuracy over baselines using fixed interpolants or non-invertible architectures.
  arXiv  Detail & Related papers  (2025-11-13T22:59:26Z)
• On the flow matching interpretability [2.816392009888047]
  We propose a framework constraining each flow step to be sampled from a known physical distribution.<n>Flow trajectories are mapped to (and constrained to traverse) the equilibrium states of the simulated physical process.<n>This demonstrates that embedding physical semantics into generative flows transforms neural trajectories into interpretable physical processes.
  arXiv  Detail & Related papers  (2025-10-24T07:26:45Z)
• Flow map matching with stochastic interpolants: A mathematical framework for consistency models [15.520853806024943]
  Flow Map Matching is a principled framework for learning the two-time flow map of an underlying generative model.<n>We show that FMM unifies and extends a broad class of existing approaches for fast sampling.
  arXiv  Detail & Related papers  (2024-06-11T17:41:26Z)
• Discrete Denoising Flows [87.44537620217673]
  We introduce a new discrete flow-based model for categorical random variables: Discrete Denoising Flows (DDFs) In contrast with other discrete flow-based models, our model can be locally trained without introducing gradient bias. We show that DDFs outperform Discrete Flows on modeling a toy example, binary MNIST and Cityscapes segmentation maps, measured in log-likelihood.
  arXiv  Detail & Related papers  (2021-07-24T14:47:22Z)
• Haar Wavelet based Block Autoregressive Flows for Trajectories [129.37479472754083]
  Prediction of trajectories such as that of pedestrians is crucial to the performance of autonomous agents. We introduce a novel Haar wavelet based block autoregressive model leveraging split couplings. We illustrate the advantages of our approach for generating diverse and accurate trajectories on two real-world datasets.
  arXiv  Detail & Related papers  (2020-09-21T13:57:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.