# Flow Map Language Models: One-step Language Modeling via Continuous Denoising

arXiv: https://arxiv.org/abs/2602.16813 · HTML: https://mlsanity.com/paper/2602.16813/

## Key facts

- Cited by 66 papers in the map (data through 14 Oct 2026).
- Placed in Discrete and text diffusion, one of 14 directions in Diffusion models.
- First posted on arXiv 18 Feb 2026.

## Placed in

- Diffusion models / [Discrete and text diffusion](https://mlsanity.com/diffusion/discrete-and-text-diffusion/)

## Built on by (most cited first, 30 of 66)

- [ELF: Embedded Language Flows](https://mlsanity.com/paper/2605.10938/) (2026)
- [LangFlow: Continuous Diffusion Rivals Discrete in Language Modeling](https://mlsanity.com/paper/2604.11748/) (2026)
- [Discrete Flow Maps](https://mlsanity.com/paper/2604.09784/) (2026)
- [Continuous Diffusion Scales Competitively with Discrete Diffusion for Language](https://mlsanity.com/paper/2605.18530/) (2026)
- [Self-conditioned Flow Map Language Models via Fixed-point Flows](https://mlsanity.com/paper/2607.00714/) (2026)
- [Beyond Single Tokens: Distilling Discrete Diffusion Models via Discrete MMD](https://mlsanity.com/paper/2603.20155/) (2026)
- [How to Train Your Latent Diffusion Language Model Jointly With the Latent Space](https://mlsanity.com/paper/2605.07933/) (2026)
- [Posterior Refinement: Fast Language Generation via Any-Order Flow Maps](https://mlsanity.com/paper/2606.24773/) (2026)
- [DiffusionGemma Technical Report](https://mlsanity.com/paper/2608.00146/) (2026)
- [CoBit: Language Modeling with Bitstream Diffusion](https://mlsanity.com/paper/2605.07013/) (2026)
- [Thinking with Looped Flows](https://mlsanity.com/paper/2609.11801/) (2026)
- [IDLM: Inverse-distilled Diffusion Language Models](https://mlsanity.com/paper/2602.19066/) (2026)
- [Scaling Categorical Flow Maps](https://mlsanity.com/paper/2605.07820/) (2026)
- [Hacking Generative Perplexity: Why Unconditional Text Evaluation Needs Distributional Metrics](https://mlsanity.com/paper/2606.08417/) (2026)
- [Spherical Flows for Sampling Categorical Data](https://mlsanity.com/paper/2605.05629/) (2026)
- [Flow Reasoning Models: Turning Flows Into Efficient Recurrent Reasoners](https://mlsanity.com/paper/2606.29150/) (2026)
- [Why Gaussian Diffusion Models Fail on Discrete Data and How to Prevent It?](https://mlsanity.com/paper/2604.02028/) (2026)
- [Contrastive Distribution Matching for Amortized Sequential Monte Carlo in Discrete Diffusion](https://mlsanity.com/paper/2605.23346/) (2026)
- [DiLaDiff: Distilled Latent-Augmented Diffusion for Language Modeling](https://mlsanity.com/paper/2605.23605/) (2026)
- [Discrete Beckmann Transport Models for One-Step Language Modeling and Reasoning](https://mlsanity.com/paper/2609.15903/) (2026)
- [Coupling Models for One-Step Discrete Generation](https://mlsanity.com/paper/2605.07193/) (2026)
- [Drifting Objectives for Refining Discrete Diffusion Language Models](https://mlsanity.com/paper/2605.19470/) (2026)
- [Recursive Scaling in Masked Diffusion Models](https://mlsanity.com/paper/2606.18022/) (2026)
- [Flow Map Denoisers: Traversing the Distortion-Perception Plane for Inverse Problems](https://mlsanity.com/paper/2606.19802/) (2026)
- [Masked Language Flow Models](https://mlsanity.com/paper/2606.27617/) (2026)
- [Sticky Jump Diffusions: A Unifying View of Masked, Continuous, and Hybrid Diffusion](https://mlsanity.com/paper/2607.10951/) (2026)
- [Simplex Relaxation for Discrete Diffusion](https://mlsanity.com/paper/2608.10615/) (2026)
- [ConvergeFlow: Language Flow with Provable Convergence to Token Embeddings](https://mlsanity.com/paper/2608.23551/) (2026)
- [Distilled Continuous Diffusion Language Models Can Write Code in Few Steps---or One](https://mlsanity.com/paper/2609.04531/) (2026)
- [DSL-LLaDA: Scaling Continuous Denoising to 8B Masked Diffusion LMs](https://mlsanity.com/paper/2606.01024/) (2026)

## Abstract (arXiv)

Language models based on discrete diffusion have attracted widespread interest for their potential to provide faster generation than autoregressive models. Despite their promise, these models typically produce samples whose quality sharply degrades in the few-step regime, preventing a dramatic speedup in practice. Here, we show that language models based on continuous flows over one-hot token embeddings can outperform discrete diffusion in both quality and speed. Importantly, our continuous formulation defines a unique flow map that can be learned directly for efficient few-step inference, a structure we show is unavailable to discrete methods. In this setting, we show that both the flow and its associated flow map can be learned with simple cross-entropy objectives that respect the simplex geometry of the data, and we identify three distinct choices for flow map distillation whose performance we compare in practice. Using these insights, we build a flow language model (FLM), a continuous flow that matches state-of-the-art discrete diffusion baselines on the One Billion Words (LM1B) and OpenWebText (OWT) datasets. We then distill FLM into a flow map language model (FMLM), whose one-step generation exceeds the 8-step quality of recent few-step discrete diffusion language models. Our work challenges the widely-held hypothesis that discrete noising processes are necessary for generative modeling over discrete modalities and paves the way toward accelerated language modeling at scale. Code is available at https://github.com/david3684/flm.