Pith. sign in

REVIEW 8 cited by

Discrete Flow Matching

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 2407.15595 v2 pith:J4OQHNX3 submitted 2024-07-22 cs.LG cs.AI

classification cs.LGcs.AI
keywords discreteflowmatchingmodelspassprobabilitydatapaths
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Despite Flow Matching and diffusion models having emerged as powerful generative paradigms for continuous variables such as images and videos, their application to high-dimensional discrete data, such as language, is still limited. In this work, we present Discrete Flow Matching, a novel discrete flow paradigm designed specifically for generating discrete data. Discrete Flow Matching offers several key contributions:(i) it works with a general family of probability paths interpolating between source and target distributions; (ii) it allows for a generic formula for sampling from these probability paths using learned posteriors such as the probability denoiser ($x$-prediction) and noise-prediction ($\epsilon$-prediction); (iii) practically, focusing on specific probability paths defined with different schedulers improves generative perplexity compared to previous discrete diffusion and flow models; and (iv) by scaling Discrete Flow Matching models up to 1.7B parameters, we reach 6.7% Pass@1 and 13.4% Pass@10 on HumanEval and 6.7% Pass@1 and 20.6% Pass@10 on 1-shot MBPP coding benchmarks. Our approach is capable of generating high-quality discrete data in a non-autoregressive fashion, significantly closing the gap between autoregressive models and discrete flow models.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

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

  1. Hacking Generative Perplexity: Why Unconditional Text Evaluation Needs Distributional Metrics

    cs.CL 2026-06 conditional novelty 7.0 of 10

    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...

  2. Coupled Continuous-Discrete Generation for Scene Text Image Super-Resolution

    cs.CV 2026-08 conditional novelty 6.0 of 10

    A shared transformer trained with continuous flow matching for images and discrete diffusion for text jointly restores scene text images and reads out their characters, removing the external OCR prior.

  3. Flexible Language Modeling in Continuous Space with Transformer-based Autoregressive Flows

    cs.LG 2025-07 conditional novelty 6.0 of 10

    TarFlowLM models language in a continuous latent space with transformer-based autoregressive normalizing flows, using mixture-CDF and Rosenblatt couplings, and reports competitive NELBO on TEXT8 and OpenWebText.

  4. CFMI: Flow Matching for Missing Data Imputation

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A conditional flow-matching model trained only on observed portions of data imputes missing entries competitively across 24 tabular and two time-series datasets.

  5. Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spaces

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A unified diffusion framework with per-modality noise clocks lets one model generate images, text, and tabular data jointly or conditionally in their native spaces.

  6. Corrector Sampling in Language Models

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A training and sampling method that lets autoregressive LLMs resample earlier tokens in a small window, improving reasoning and coding benchmark scores by about 10% relative after a 100B-token fine-tuning.

  7. Accelerated Sampling from Masked Diffusion Models via Entropy Bounded Unmasking

    cs.LG 2025-05 conditional novelty 6.0 of 10

    EB-Sampler dynamically unmasks multiple low-entropy tokens per function evaluation, accelerating masked diffusion model sampling by 2-3x with negligible accuracy loss.

  8. SynBridge: Bridging Reaction States via Discrete Flow for Bidirectional Reaction Prediction

    cs.LG 2025-07 conditional novelty 5.0 of 10

    A bidirectional discrete flow matching model, SynBridge, predicts reaction products and reactants on graph representations and reports state-of-the-art Top-k accuracy on USPTO-50K, USPTO-MIT, and Pistachio.

Pith tools