Sign inGet started
Repository · GitHub

SJTU-DENG-Lab/Discrete-Diffusion-Forcing

[ICLR 2026] Discrete Diffusion Forcing (D2F): dLLMs Can Do Faster-Than-AR Inference

OwnerSJTU-DENG-Lab
License (as declared)MIT
Stars263
Forks20
Main languagePython
Created5 August 2025
Last updated at source3 February 2026
pythondllminference-accelerationllm
Embed this entry
<iframe src="https://silytics.si/embed/item/79604c33-b3f7-4751-bcdd-725027112849" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Stars, last 5 days

263 now. Counts as reported by the source, snapshotted daily by Silytics.

Silytics shows public metadata from GitHub and links to the original. Information may be incomplete or out of date. Last refreshed 20 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.