Neural Continuous-Time Markov Chain: Discrete Diffusion via Decoupled Jump Timing and Direction

• URL: http://arxiv.org/abs/2604.15694v1
• Date: Fri, 17 Apr 2026 04:40:19 GMT
• Title: Neural Continuous-Time Markov Chain: Discrete Diffusion via Decoupled Jump Timing and Direction
• Abstract summary: We propose textbfNeural CTMC, which parameterizes the reverse process through an emphexit rate (when to jump) and a emphjump distribution (where to jump) using two dedicated network heads.<n>We show that the evidence lower bound (ELBO) differs from a path-space KL divergence between the true and learned reverse processes by a $$-independent constant.<n>We also show that the tractable conditional surrogate preserves the gradients and minimizers of the corresponding marginal reverse-process objective under standard regularity assumptions.
• Score: 18.20305761007799
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Discrete diffusion models based on continuous-time Markov chains (CTMCs) have shown strong performance on language and discrete data generation, yet existing approaches typically parameterize the reverse rate matrix as a single object -- via concrete scores, clean-data predictions ($x_0$-parameterization), or denoising distributions -- rather than aligning the parameterization with the intrinsic CTMC decomposition into jump timing and jump direction. Since a CTMC is fundamentally a Poisson process fully determined by these two quantities, decomposing along this structure is closer to first principles and naturally leads to our formulation. We propose \textbf{Neural CTMC}, which separately parameterizes the reverse process through an \emph{exit rate} (when to jump) and a \emph{jump distribution} (where to jump) using two dedicated network heads. We show that the evidence lower bound (ELBO) differs from a path-space KL divergence between the true and learned reverse processes by a $θ$-independent constant, so that the training objective is fully governed by the exit rate and jump distribution we parameterize. Moreover, this KL factorizes into a Poisson KL for timing and a categorical KL for direction. We further show that the tractable conditional surrogate preserves the gradients and minimizers of the corresponding marginal reverse-process objective under standard regularity assumptions. Our theoretical framework also covers masked and GIDD-style noise schedules. Empirically, while the uniform forward process has been explored in prior work, our model, to our best of the knowledge, is the first pure-uniform method to outperform mask-based methods on the OpenWebText dataset.To facilitate reproducibility, we release our pretrained weights at https://huggingface.co/Jiangxy1117/Neural-CTMC.

Related papers

• Scale-Consistent Posterior Dynamics for Diffusion Inverse Problems [16.685352002333225]
  Posterior sampling with a pretrained diffusion prior is governed by a conditional score whose likelihood component is generally intractable.<n>We show that a noise-conditioned path whose targets approach the clean posterior produces a continuous surrogate SDE.<n>Experiments on FFHQ and ImageNet with 100 score evaluations demonstrate competitive reconstruction fidelity for superresolution and deblurring.
  arXiv  Detail & Related papers  (2026-08-15T09:38:41Z)
• UNIFUSION: Adapting Autoregressive Language Models into Discrete Diffusion under a Unified Reverse-Rate Objective [17.48959208263029]
  We propose a simple continual pre-training approach for adapting pretrained GPT2 checkpoints to uniform-noise diffusion.<n>ours steadily improves the trade-off between generative perplexity (GenPPL) and unigram entropy as the sampling budget increases.<n>At both scales, ours also achieves the highest WinoGrande, SIQA, and BBH accuracy among the compared diffusion models.
  arXiv  Detail & Related papers  (2026-07-27T14:40:26Z)
• What Does a Discrete Diffusion Model Learn? [71.03603607324338]
  discrete diffusion model learns: a denoiser, a score ratio, or a bridge plug-in predictor.<n>We start with a rigorous derivation of the continuous-time Markov chain (CTMC) ELBO for any noising process.<n>Every identity is verified numerically, without approximation, on an exactly solvable model.
  arXiv  Detail & Related papers  (2026-07-06T17:56:11Z)
• Inference-Time Alignment of Diffusion Models via Trust-Region Iterative Twisted Sequential Monte Carlo [15.105260031413698]
  We study inference-time alignment for diffusion-based generative models.<n>We propose a trust-region framework for learning twisting functions in SMC-based inference-time alignment.
  arXiv  Detail & Related papers  (2026-05-24T15:08:52Z)
• Why SGD is not Brownian Motion: A New Perspective on Stochastic Dynamics [92.39053980710702]
  Gradient Descent (SGD) is commonly modeled as a Langevin process, assuming that minibatch noise acts as Brownian motion.<n>This approximation relies on a continuous-time limit and a sqrt(eta) noise scaling that does not match the discrete SGD update at finite learning rate.<n>We propose an alternative formulation of SGD as deterministic dynamics in a fluctuating loss landscape induced by minibatch sampling.
  arXiv  Detail & Related papers  (2026-05-21T15:50:40Z)
• One-Step Face Restoration via Shortcut-Enhanced Coupling Flow [2.8265172105754104]
  We propose Shortcut-enhanced Coupling flow for Face Restoration (SCFlowFR)<n>It explicitly models the LQ--HQ dependency, minimizing path crossovers and promoting near-linear transport.<n> Experiments demonstrate that SCFlowFR achieves state-of-the-art one-step face restoration quality with inference speed comparable to traditional non-diffusion methods.
  arXiv  Detail & Related papers  (2026-03-04T02:11:15Z)
• Self-Rewarding Sequential Monte Carlo for Masked Diffusion Language Models [58.946955321428845]
  This work presents self-rewarding sequential Monte Carlo (SMC)<n>Our algorithm stems from the observation that most existing MDLMs rely on a confidence-based sampling strategy.<n>We introduce the trajectory-level confidence as a self-rewarding signal for assigning particle importance weights.
  arXiv  Detail & Related papers  (2026-02-02T09:21:45Z)
• Stratified Hazard Sampling: Minimal-Variance Event Scheduling for CTMC/DTMC Discrete Diffusion and Flow Models [0.0]
  Stratified Hazard Sampling Sampling (SHS) models per-token edits as events driven by cumulative hazard (CTMC) or cumulative jump mass (DTMC)<n>SHS models per-token edits as events driven by cumulative hazard (CTMC) or cumulative jump mass (DTMC) and places events by stratifying this cumulative quantity.<n>We also introduce a phase-allocation variant for blacklist-style lexical constraints that prioritizes early edits at high-risk positions to mitigate late-masking artifacts.
  arXiv  Detail & Related papers  (2026-01-06T08:19:02Z)
• Foundations of Diffusion Models in General State Spaces: A Self-Contained Introduction [54.95522167029998]
  This article is a self-contained primer on diffusion over general state spaces.<n>We develop the discrete-time view (forward noising via Markov kernels and learned reverse dynamics) alongside its continuous-time limits.<n>A common variational treatment yields the ELBO that underpins standard training losses.
  arXiv  Detail & Related papers  (2025-12-04T18:55:36Z)
• Diffusion Models: A Mathematical Introduction [3.8673630752805437]
  We present a self-contained derivation of diffusion-based generative models.<n>We construct denoising diffusion probabilistic models from first principles.<n>Readers can both follow the theory and implement the corresponding algorithms in practice.
  arXiv  Detail & Related papers  (2025-11-13T16:20:52Z)
• Almost Linear Convergence under Minimal Score Assumptions: Quantized Transition Diffusion [25.542593757387095]
  We propose Quantized Transition Diffusion (QTD), a novel approach that integrates data quantization with discrete diffusion dynamics.<n>Our method first transforms the continuous data distribution $p_*$ into a discrete one $q_*$ via histogram approximation and binary encoding.<n>For reverse-time sampling, we introduce a textittruncated uniformization technique to simulate the reverse CTMC.
  arXiv  Detail & Related papers  (2025-05-28T02:10:11Z)
• Rectified Diffusion Guidance for Conditional Generation [94.83538269086613]
  We revisit the theory behind CFG and rigorously confirm that the improper combination coefficients (textiti.e.) brings about expectation shift the generative distribution.<n>We show that our approach enjoys a textbftextitform solution given the strength.<n> Empirical evidence on real-world data demonstrate the compatibility of our design with existing state-of-the-art diffusion models.
  arXiv  Detail & Related papers  (2024-10-24T13:41:32Z)
• Generative Fractional Diffusion Models [53.36835573822926]
  We introduce the first continuous-time score-based generative model that leverages fractional diffusion processes for its underlying dynamics. Our evaluations on real image datasets demonstrate that GFDM achieves greater pixel-wise diversity and enhanced image quality, as indicated by a lower FID.
  arXiv  Detail & Related papers  (2023-10-26T17:53:24Z)
• Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network [59.79008107609297]
  We propose in this paper to approximate the joint posterior over the structure of a Bayesian Network. We use a single GFlowNet whose sampling policy follows a two-phase process. Since the parameters are included in the posterior distribution, this leaves more flexibility for the local probability models.
  arXiv  Detail & Related papers  (2023-05-30T19:16:44Z)
• Score-based Continuous-time Discrete Diffusion Models [102.65769839899315]
  We extend diffusion models to discrete variables by introducing a Markov jump process where the reverse process denoises via a continuous-time Markov chain. We show that an unbiased estimator can be obtained via simple matching the conditional marginal distributions. We demonstrate the effectiveness of the proposed method on a set of synthetic and real-world music and image benchmarks.
  arXiv  Detail & Related papers  (2022-11-30T05:33:29Z)

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.