Papers › DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models

DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models

28 Nov 2022arXiv:2211.15029archive 2025-07-28

Zhengfu He, Tianxiang Sun, Kuanning Wang, Xuanjing Huang, Xipeng Qiu

We present DiffusionBERT, a new generative masked language model based on discrete diffusion models. Diffusion models and many pre-trained language models have a shared training objective, i.e., denoising, making it possible to combine the two powerful models and enjoy the best of both worlds. On the one hand, diffusion models offer a promising training strategy that helps improve the generation quality. On the other hand, pre-trained denoising language models (e.g., BERT) can be used as a good initialization that accelerates convergence. We explore training BERT to learn the reverse process of a discrete diffusion process with an absorbing state and elucidate several designs to improve it. First, we propose a new noise schedule for the forward diffusion process that controls the degree of noise added at each step based on the information of each token. Second, we investigate several designs of incorporating the time step into BERT. Experiments on unconditional text generation demonstrate that DiffusionBERT achieves significant improvement over existing diffusion models for text (e.g., D3PM and Diffusion-LM) and previous generative masked language models in terms of perplexity and BLEU score.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 11 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 9 ran (8 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

hzfinfdu/diffusion-bert officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 11 samples, 9 ran (1 instrument-failed) · 2 unverified 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

11 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
8ran
2unverified

Licence: 2 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from hzfinfdu/diffusion-bert. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

hzfinfdu/diffusion-bert official repository 11 samples, 9 ran (1 instrument-failed) · 2 unverified
create_position_ids_from_input_ids in 41 papers
census: 5 implementations from 6 papers, 1 distinct output on one shared input
models/modeling_roberta.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 38f46ef4e03fee1c · report fixture: signature input_ids:Tensor/2/int, padding_idx:int/0/int, past_key_values_length:int/0/int · returned Tensor · level recorded 2026-09-24
cross_entropy_with_probs losses.py ran Apache-2.0 (permissive) · 110e847251e7cce1 · report fixture: signature probs:Tensor/3/float, targets:Tensor/2/int, epsilon:float/0/float · returned Tensor · level recorded 2026-09-25
dist1 compute_metric.py ran Apache-2.0 (permissive) · 841fce93f14f6675 · report fixture: signature hypn:list/1/str, n:int/0/int · returned float64 · level recorded 2026-09-25
div4 compute_metric.py ran Apache-2.0 (permissive) · 35a119672af367f4 · report fixture: signature hypn:list/1/str, n:int/0/int · returned float · level recorded 2026-09-25
get_bleu in 5 papers compute_metric.py ran fingerprinted Apache-2.0 (permissive) · 7b8175dc450ebd39 · report fixture: signature recover:str/0/str, reference:str/0/str · returned float · level recorded 2026-09-25
get_timestep_embedding in 138 papers
census: 11 implementations from 15 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
models/modeling_bert_new_timestep.py ran fingerprinted Apache-2.0 (permissive) · f93c2d73d355d807 · report fixture: signature timesteps:Tensor/1/float, dim:int/0/int, max_period:int/0/int · returned Tensor · level recorded 2026-09-25
kl_divergence_with_probs losses.py ran fingerprinted Apache-2.0 (permissive) · 24387783361281e8 · report fixture: signature p:Tensor/2/float, q:Tensor/2/float, epsilon:float/0/float · returned Tensor · level recorded 2026-09-25
p_forward diffusion_condition.py ran Apache-2.0 (permissive) · 1dd4ba483b72927b · report fixture: signature denoise_fn:callable/0/?, x_t:Tensor/2/int, t:Tensor/0/int, diffusion:Diffusion/0/?, predict_x0:bool/0/bool, return_x0:bool/0/bool, return_logits:bool/0/bool, special_case_x0:bool/0/bool, transition_probs:NoneType/0/?, transition_probs_in_logits:bool/0/bool, maximum_likelihood:bool/0/bool, epsilon:float/0/float, step_size:int/0/int, word_freq_logits:NoneType/0/? · returned Tensor · level recorded 2026-09-25
process_fn_in_collate compute_elbo.py ran fingerprinted Apache-2.0 (permissive) · 59f7bb96a85f250f · report fixture: signature wf:Tensor/2/float · returned Tensor · level recorded 2026-09-25
collate_fn in 500 papers compute_elbo.py unverified Apache-2.0 (permissive) · 6f15d047a8622d18 · report
load_tf_weights_in_bert in 135 papers models/modeling_bert.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · d009b630f4496e64 · report

Tasks

DenoisingLanguage ModelingLanguage ModellingText Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionAttention DropoutBERTDense ConnectionsDiffusionDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSoftmaxWeight DecayWordPiece

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