mlsanityData to 14 Oct 2026

Towards Latent Diffusion Suitable For Text

arXiv 2601.16220 ↗First posted 7 Jan 2026cs.CL cs.LG stat.MLcited by 1

On the map: Diffusion models → Discrete and text diffusion

Abstract (arXiv)

Language diffusion models aim to improve sampling speed and coherence over autoregressive LLMs. We introduce Neural Flow Diffusion Models for language generation, an extension of NFDM that enables the straightforward application of continuous diffusion models to discrete state spaces. NFDM learns a multivariate forward process from the data, ensuring that the forward process and generative trajectory are a good fit for language modeling. Our model substantially reduces the likelihood gap with autoregressive models of the same size, while achieving sample quality comparable to that of previous latent diffusion models.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Discrete and text diffusion, one of 14 directions in Diffusion models. Builds on 16 of its 28 references that are in the map. First posted on arXiv 7 Jan 2026.

Builds on

16 of 28 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024TEncDM: Understanding the Properties of the Diffusion Model in the Space of Language Model Encodings29 Feb
  2. 2023Likelihood-Based Diffusion Language Models30 May
  3. 2023A Cheaper and Better Diffusion Language Model with Soft-Masked Noise10 Apr
  4. 2022Latent Diffusion for Language Generation19 Dec
  5. 2022Continuous diffusion for categorical data28 Nov
  6. 2021Autoregressive Diffusion Models5 Oct

Other references · 10

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  4. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,027
  5. 2017Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learningcited by 950
  6. 2021MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontierscited by 470
  7. 2022A Continuous Time Framework for Discrete Denoising Modelscited by 451
  8. 2024Flow Matching with General Discrete Paths: A Kinetic-Optimal Perspectivecited by 57
  9. 2023Diffusion Models With Learned Adaptive Noisecited by 51
  10. 2024Neural Flow Diffusion Models: Learnable Forward Process for Improved Diffusion Modellingcited by 45

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Recursive Scaling in Masked Diffusion Modelscited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2024Scaling Diffusion Language Models via Adaptation from Autoregressive Models
  2. 2023A Survey of Diffusion Models in Natural Language Processing
  3. 2025Latent-Augmented Discrete Diffusion Models
  4. 2025A Survey on Diffusion Language Models
  5. 2023Diffusion Models for Non-autoregressive Text Generation: A Survey
  6. 2026How to Train Your Latent Diffusion Language Model Jointly With the Latent Space
  7. 2025State Fourier Diffusion Language Model (SFDLM): A Scalable, Novel Iterative Approach to Language Modeling
  8. 2025Discrete Diffusion Models for Language Generation