From AR to Diffusion: Efficiently Adapting Large Language Models with Strictly Causal and Elastic Horizons
A new framework called FLUID adapts autoregressive language models to diffusion models for efficient parallel text generation, using Strictly Causal Alignment to reuse GPT checkpoints and Elastic Horizons to dynamically adjust denoising steps. It achieves state-of-the-art performance with significantly reduced training costs.
Article intelligence
Key points
- FLUID bridges AR and diffusion models by enforcing Strictly Causal Alignment, enabling initialization from GPT-style checkpoints.
- Elastic Horizons uses entropy to dynamically adapt denoising strides based on local information density.
- The method achieves state-of-the-art results while reducing training costs by orders of magnitude.
- Code is available on GitHub; paper accepted at ACL 2026.
Why it matters
This matters because FLUID bridges AR and diffusion models by enforcing Strictly Causal Alignment, enabling initialization from GPT-style checkpoints.
Technical impact
May affect model selection, inference cost, product capability, and evaluation benchmarks.
[2605.27387] From AR to Diffusion: Efficiently Adapting Large Language Models with Strictly Causal and Elastic Horizons
[Submitted on 11 Apr 2026]
Title:From AR to Diffusion: Efficiently Adapting Large Language Models with Strictly Causal and Elastic Horizons
View a PDF of the paper titled From AR to Diffusion: Efficiently Adapting Large Language Models with Strictly Causal and Elastic Horizons, by Xiangyu Ma and 3 other authors
View PDF HTML (experimental)
Abstract:Diffusion models promise efficient parallel text generation but rely on bidirectional attention, creating a structural mismatch with pre-trained Autoregressive (AR) models. This incompatibility precludes reusing robust AR priors, necessitating prohibitive pre-training from scratch. To bridge this gap, we propose FLUID, a framework that efficiently adapts AR backbones to the diffusion paradigm. By enforcing Strictly Causal Alignment, FLUID enables seamless initialization from standard GPT-style checkpoints, circumventing the need for massive pre-training. Furthermore, we introduce Elastic Horizons, an entropy-driven mechanism that dynamically modulates denoising strides based on local information density rather than fixed schedules. Experiments demonstrate that FLUID achieves state-of-the-art performance while reducing training costs by orders of magnitude, effectively reconciling established AR foundations with efficient parallel generation. Our code is available at this https URL.
Comments: Accepted by ACL 2026
Subjects:
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
Cite as: arXiv:2605.27387 [cs.CL]
(or arXiv:2605.27387v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2605.27387
arXiv-issued DOI via DataCite
Submission history
From: Xiangyu Ma [view email] [v1] Sat, 11 Apr 2026 13:18:27 UTC (1,710 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled From AR to Diffusion: Efficiently Adapting Large Language Models with Strictly Causal and Elastic Horizons, by Xiangyu Ma and 3 other authors
View PDF
HTML (experimental)
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?)