Methods › Natural Language Processing › Language Models › Diffusion

Diffusion

13,848 papers tagged archive 2025-07-28

Introduced by Jonathan Ho et al. in Denoising Diffusion Probabilistic Models

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound (https://arxiv.org/abs/2006.11239).

PaperSource

In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.

Near matches the lookup lists, each a different name: Q-Diffusion; E-Diffusion; ρ-DIFFUSION; Diffusion-4K; AR-Diffusion; Co-Diffusion; DIFFUSION-MF; PN-Diffusion.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 13,848 · with a code link: 5,365 · where Syntology ran a sample: 2,249 (1,908 with a run with no instrument failure, 341 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (2,249 of 13,848 tagged: 1,908 with a run with no instrument failure, 341 where every run was a failure of Syntology's instrument)

Page 1 of 139: papers 1 to 100 of 13,848, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

20 shown of 1,474 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Image Generation2,525
Denoising2,447
Video Generation666
Diversity549
Text-to-Image Generation543
Text to Image Generation485
Super-Resolution399
Object345
model333
Data Augmentation326
Semantic Segmentation318
Language Modelling313
Decoder310
Segmentation283
3D Generation263
Language Modeling235
Attribute222
GPU203
Image Restoration201
Text to 3D197

Usage over time archive 2025-07-28

Papers per year tagged with Diffusion: 2020 to 2025, peak 5,829 5,829 0 2020: 167 papers 2020 2021: 434 papers 2021 2022: 857 papers 2022 2023: 3354 papers 2023 2024: 5829 papers 2024 2025: 3207 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (13,848 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Language ModelsImage Generation Models

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