AI News HubLIVE
Original source2 min read

Adaptive Multi-Step Lookahead Decoding for Diffusion Language Models

This paper introduces AdaLook, an adaptive lookahead framework for masked diffusion language models. By dynamically determining rollout depth based on candidate-score variance and enabling branch expansion, AdaLook achieves a better accuracy-efficiency trade-off than existing one-step lookahead methods.

SourcearXiv Computational LinguisticsAuthor: Yingqian Cui, Wei Deng, Lantao Mei, Hang Li, Charu C. Aggarwal, Hui Liu, Yue Xing

-->

[Submitted on 17 Jul 2026]

Title:Adaptive Multi-Step Lookahead Decoding for Diffusion Language Models

View a PDF of the paper titled Adaptive Multi-Step Lookahead Decoding for Diffusion Language Models, by Yingqian Cui and 6 other authors

View PDF HTML (experimental)

Abstract:Masked diffusion language models (DLMs) enable parallel text generation by iteratively refining masked tokens, offering a promising alternative to autoregressive decoding. Recent lookahead-based decoding methods improve the accuracy--efficiency trade-off by exploring future decoding states before committing token updates. However, existing approaches mainly rely on shallow one-step lookahead, which optimizes immediate information gain but can be suboptimal for longer-horizon decoding trajectories. Meanwhile, we find that a naive extension for deeper lookahead is also ineffective, as fixed-depth rollout introduces additional computation and cannot adapt to heterogeneous intermediate decoding states. Thus, in this work, we propose AdaLook, an adaptive lookahead framework for DLM decoding. AdaLook dynamically determines whether to continue rollout based on candidate-score variance and further enables branch expansion when intermediate rollout states require additional exploration. This design avoids unnecessary deep rollout while allowing the decoder to re-trigger lookahead from informative intermediate states. Experiments on various benchmarks and models demonstrate that AdaLook achieves a better accuracy--decoding steps trade-off than existing one-step lookahead decoding methods.

Subjects:

Computation and Language (cs.CL); Machine Learning (cs.LG)

Cite as: arXiv:2607.15655 [cs.CL]

(or arXiv:2607.15655v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2607.15655

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Yingqian Cui [view email] [v1] Fri, 17 Jul 2026 06:04:04 UTC (1,318 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Adaptive Multi-Step Lookahead Decoding for Diffusion Language Models, by Yingqian Cui and 6 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CL

new | recent | 2026-07

Change to browse by:

cs cs.LG

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?)