Discrete Tilt Matching

PaulHoule1 pts0 comments

[2604.18739] Discrete Tilt Matching

-->

Computer Science > Machine Learning

arXiv:2604.18739 (cs)

[Submitted on 20 Apr 2026 (v1), last revised 19 May 2026 (this version, v3)]

Title:Discrete Tilt Matching

Authors:Yuyuan Chen, Shiyi Wang, Peter Potaptchik, Jaeyeon Kim, Michael S. Albergo<br>View a PDF of the paper titled Discrete Tilt Matching, by Yuyuan Chen and 4 other authors

View PDF<br>HTML (experimental)

Abstract:Masked diffusion large language models (dLLMs) are a promising alternative to autoregressive generation. While reinforcement learning (RL) methods have recently been adapted to dLLM fine-tuning, their objectives typically depend on sequence-level marginal likelihoods, which are intractable for masked diffusion models. To address this, we derive Discrete Tilt Matching (DTM), a likelihood-free method that recasts dLLM fine-tuning as state-level matching of local unmasking posteriors under reward tilting. DTM takes the form of a weighted cross-entropy objective with explicit minimizer, and admits control variates that improve training stability. On a synthetic maze-planning task, we analyze how DTM's annealing schedule and control variates affect training stability and prevent mode collapse. At scale, fine-tuning LLaDA-8B-Instruct with DTM yields strong gains on Sudoku and Countdown while remaining competitive on MATH500 and GSM8K.

Subjects:

Machine Learning (cs.LG); Machine Learning (stat.ML)

Cite as:<br>arXiv:2604.18739 [cs.LG]

(or<br>arXiv:2604.18739v3 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2604.18739

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Yuyuan Chen [view email]<br>[v1]<br>Mon, 20 Apr 2026 18:43:37 UTC (6,659 KB)

[v2]<br>Sat, 16 May 2026 03:48:01 UTC (6,659 KB)

[v3]<br>Tue, 19 May 2026 01:39:31 UTC (6,659 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Discrete Tilt Matching, by Yuyuan Chen and 4 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.LG

next >

new<br>recent<br>| 2026-04

Change to browse by:

cs<br>stat<br>stat.ML

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

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?)

IArxiv recommender toggle

IArxiv Recommender<br>(What is IArxiv?)

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? |<br>Disable MathJax (What is MathJax?)

toggle arxiv matching discrete tilt view

Related Articles