Papers › Simplified and Generalized Masked Diffusion for Discrete Data

Simplified and Generalized Masked Diffusion for Discrete Data

6 Jun 2024arXiv:2406.04329archive 2025-07-28

Jiaxin Shi, Kehang Han, Zhe Wang, Arnaud Doucet, Michalis K. Titsias

Masked (or absorbing) diffusion is actively explored as an alternative to autoregressive models for generative modeling of discrete data. However, existing work in this area has been hindered by unnecessarily complex model formulations and unclear relationships between different perspectives, leading to suboptimal parameterization, training objectives, and ad hoc adjustments to counteract these issues. In this work, we aim to provide a simple and general framework that unlocks the full potential of masked diffusion models. We show that the continuous-time variational objective of masked diffusion models is a simple weighted integral of cross-entropy losses. Our framework also enables training generalized masked diffusion models with state-dependent masking schedules. When evaluated by perplexity, our models trained on OpenWebText surpass prior diffusion language models at GPT-2 scale and demonstrate superior performance on 4 out of 5 zero-shot language modeling tasks. Furthermore, our models vastly outperform previous discrete diffusion models on pixel-level image modeling, achieving 2.75 (CIFAR-10) and 3.40 (ImageNet 64x64) bits per dimension that are better than autoregressive models of similar sizes. Our code is available at https://github.com/google-deepmind/md4.

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="2406.04329")

Code

Syntology Ran 6 of 21 code samples harvested from 1 repository linked to this paper; 15 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · our draft was wrong; 3 ran · fixture could not drive it; 1 ran with no contract checked.

By repository: official repository: 21 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

google-deepmind/md4 officialmentioned in paperjax 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

21 samples harvested; 6 ran; 1 honoured the contract we drafted; 15 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.

1ran · honoured contract
1ran · our draft was wrong
3ran · fixture could not drive it
1ran
15unverified

Licence: 0 of the 21 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 google-deepmind/md4. “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.

MaskingSchedule google-deepmind/md4/md4/models/diffusion/md4.py official repository ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 66a81c44aa3c341b · report
get_timestep_embedding google-deepmind/md4/md4/models/diffusion/md4.py official repository ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · 84db74ee09e0bda4 · report
jax_unstack google-deepmind/md4/md4/models/diffusion/md4.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · b6960d9da81c946a · report
precompute_freqs_cis google-deepmind/md4/md4/models/diffusion/md4.py official repository ran · honoured contract fingerprinted Apache-2.0 (permissive) · 8873a5201399b10b · report
repeat_kv google-deepmind/md4/md4/models/diffusion/md4.py official repository ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · 4a1c75a9a5f46c4f · report
reshape_for_broadcast google-deepmind/md4/md4/models/diffusion/md4.py official repository ran · fixture could not drive it Apache-2.0 (permissive) · 0dc13509bbb03398 · report
Attention google-deepmind/md4/md4/models/diffusion/md4.py official repository unverified Apache-2.0 (permissive) · b5d57c4d33c17740 · report
CondEmbedding google-deepmind/md4/md4/models/diffusion/md4.py official repository unverified Apache-2.0 (permissive) · e341090d86d921b9 · report
DiscreteClassifier google-deepmind/md4/md4/models/diffusion/md4.py official repository unverified Apache-2.0 (permissive) · b74decb1e729d273 · report
Dropout1d google-deepmind/md4/md4/models/diffusion/md4.py official repository unverified Apache-2.0 (permissive) · d8f8ff9226830df3 · report
FeedForward google-deepmind/md4/md4/models/diffusion/md4.py official repository unverified Apache-2.0 (permissive) · 170abc34ff9d4f81 · report
MD4 google-deepmind/md4/md4/models/diffusion/md4.py official repository unverified Apache-2.0 (permissive) · 4b01cbf6a3ec21a6 · report
ModelArgs google-deepmind/md4/md4/models/diffusion/md4.py official repository unverified Apache-2.0 (permissive) · be5a00527b2e82e0 · report
RMSNorm google-deepmind/md4/md4/models/diffusion/md4.py official repository unverified Apache-2.0 (permissive) · a75e172eea6d85f1 · report
ResBlock google-deepmind/md4/md4/models/diffusion/md4.py official repository unverified Apache-2.0 (permissive) · 2db631aa126ebf6e · report
SelfAttention google-deepmind/md4/md4/models/diffusion/md4.py official repository unverified Apache-2.0 (permissive) · daf4ef755a1978a3 · report
Transformer google-deepmind/md4/md4/models/diffusion/md4.py official repository unverified Apache-2.0 (permissive) · 87a69858dd77c308 · report
TransformerBlock google-deepmind/md4/md4/models/diffusion/md4.py official repository unverified Apache-2.0 (permissive) · 7a351fb6b29e26ac · report
UNet google-deepmind/md4/md4/models/diffusion/md4.py official repository unverified Apache-2.0 (permissive) · 35c08ff52d7e2f6b · report
UNet5DWrapper google-deepmind/md4/md4/models/diffusion/md4.py official repository unverified Apache-2.0 (permissive) · a2d820814fa59452 · report
apply_rotary_emb google-deepmind/md4/md4/models/diffusion/md4.py official repository unverified Apache-2.0 (permissive) · 582256db3844c9de · report

Tasks

Language ModelingLanguage Modelling

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Language Modelling OpenWebText GenMD4 eval_perplexity 21.80 #10 of 12 Archive leaderboard report
Language Modelling OpenWebText GenMD4 parameters 131M #10 of 12 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AdamAttentionAttention DropoutBPECosine AnnealingDense ConnectionsDiffusionDiscriminative Fine-TuningDropoutGPT-2HOCLayer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionResidual ConnectionSoftmaxWeight Decay

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