FlowLM: Few-Step Language Modeling via Diffusion-to-Flow Adaptation
FlowLM converts pre-trained diffusion language models into flow matching models via efficient fine-tuning, enabling high-quality few-step generation that rivals 2,000-step diffusion sampling with minimal training epochs.
[2605.20199] FlowLM: Few-Step Language Modeling via Diffusion-to-Flow Adaptation
[Submitted on 6 Apr 2026]
Title:FlowLM: Few-Step Language Modeling via Diffusion-to-Flow Adaptation
View a PDF of the paper titled FlowLM: Few-Step Language Modeling via Diffusion-to-Flow Adaptation, by Runzhe Zhang and 4 other authors
View PDF
Abstract:We present FlowLM, a flow matching language model transformed from pre-trained diffusion language models via efficient fine-tuning. By re-aligning the curved sampling trajectories of diffusion models into straight-line flows, FlowLM enables high quality few-step generation that rivals or even outperforms the quality of 2,000-step diffusion sampling with very few training epochs. Remarkably, finetuned FlowLM reaches performance saturation with only half as many training epochs as training from scratch, both approaches greatly outperforming the original diffusion model, thereby validating our method. Furthermore, we validate a more effective training objective for flow matching: predicting clean data to consistently guide the sampling process towards the true data distribution. Empirical results demonstrate that our approach is highly effective for high-quality, few-step text generation.
Comments: 26 pages, 11 figures
Subjects:
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
Cite as: arXiv:2605.20199 [cs.CL]
(or arXiv:2605.20199v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2605.20199
arXiv-issued DOI via DataCite
Submission history
From: Runzhe Zhang [view email] [v1] Mon, 6 Apr 2026 10:36:22 UTC (3,537 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled FlowLM: Few-Step Language Modeling via Diffusion-to-Flow Adaptation, by Runzhe Zhang and 4 other authors
View PDF
TeX Source
view license
Current browse context:
cs.CL
new | recent | 2026-05
Change to browse by:
cs cs.AI
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)