Papers › Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion

Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion

1 Jul 2024arXiv:2407.01392archive 2025-07-28

Boyuan Chen, Diego Marti Monso, Yilun Du, Max Simchowitz, Russ Tedrake, Vincent Sitzmann

This paper presents Diffusion Forcing, a new training paradigm where a diffusion model is trained to denoise a set of tokens with independent per-token noise levels. We apply Diffusion Forcing to sequence generative modeling by training a causal next-token prediction model to generate one or several future tokens without fully diffusing past ones. Our approach is shown to combine the strengths of next-token prediction models, such as variable-length generation, with the strengths of full-sequence diffusion models, such as the ability to guide sampling to desirable trajectories. Our method offers a range of additional capabilities, such as (1) rolling-out sequences of continuous tokens, such as video, with lengths past the training horizon, where baselines diverge and (2) new sampling and guiding schemes that uniquely profit from Diffusion Forcing's variable-horizon and causal architecture, and which lead to marked performance gains in decision-making and planning tasks. In addition to its empirical success, our method is proven to optimize a variational lower bound on the likelihoods of all subsequences of tokens drawn from the true joint distribution. Project website: https://boyuan.space/diffusion-forcing

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2407.01392")

Code

Syntology Ran 5 of 5 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 2 ran · violated contract; 1 ran · our draft was wrong; 2 ran with no contract checked.

By repository: official repository: 5 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

buoyancy99/diffusion-forcing officialmentioned in papermentioned on GitHubpytorchNOASSERTION report
leffff/diffusion-forcing mentioned on GitHubMIT report
skyworkai/skyreels-v2 mentioned on GitHubpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

5 samples harvested; 5 ran; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · violated contract
1ran · our draft was wrong
2ran

Licence: 5 of the 5 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from buoyancy99/diffusion-forcing. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

default buoyancy99/diffusion-forcing/algorithms/diffusion_forcing/models/utils.py official repository ran · violated contract no licence file found · pointer only · 915fbeb88e13d4a3 · report
exists buoyancy99/diffusion-forcing/algorithms/diffusion_forcing/models/utils.py official repository ran · violated contract no licence file found · pointer only · aa5486a3650902d8 · report
extract buoyancy99/diffusion-forcing/algorithms/diffusion_forcing/models/utils.py official repository ran licence not identified · pointer only · f45e6ade28d9233f · report
get_timestep_embedding buoyancy99/diffusion-forcing/algorithms/diffusion_forcing/models/embeddings.py official repository ran licence not identified · pointer only · d2ab2ee4d21e2ed0 · report
once buoyancy99/diffusion-forcing/algorithms/diffusion_forcing/models/attention.py official repository ran · our draft was wrong no licence file found · pointer only · 52e10a7d6b0fa036 · report

Tasks

Decision MakingPrediction

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DiffusionSET

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections