Papers › Spontaneous Symmetry Breaking in Generative Diffusion Models

Spontaneous Symmetry Breaking in Generative Diffusion Models

31 May 2023NeurIPS 2023 11arXiv:2305.19693archive 2025-07-28

Gabriel Raya, Luca Ambrogioni

Generative diffusion models have recently emerged as a leading approach for generating high-dimensional data. In this paper, we show that the dynamics of these models exhibit a spontaneous symmetry breaking that divides the generative dynamics into two distinct phases: 1) A linear steady-state dynamics around a central fixed-point and 2) an attractor dynamics directed towards the data manifold. These two "phases" are separated by the change in stability of the central fixed-point, with the resulting window of instability being responsible for the diversity of the generated samples. Using both theoretical and empirical evidence, we show that an accurate simulation of the early dynamics does not significantly contribute to the final generation, since early fluctuations are reverted to the central fixed point. To leverage this insight, we propose a Gaussian late initialization scheme, which significantly improves model performance, achieving up to 3x FID improvements on fast samplers, while also increasing sample diversity (e.g., racial composition of generated CelebA images). Our work offers a new way to understand the generative dynamics of diffusion models that has the potential to bring about higher performance and less biased fast-samplers.

PaperPDFConference PDFCodeCode 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="2305.19693")

Code

Syntology Ran 6 of 19 code samples harvested from 1 repository linked to this paper; 13 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 4 ran with no contract checked.

By repository: official repository: 19 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.

gabrielraya/symmetry_breaking_diffusion_models officialmentioned in paperjaxMIT 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

19 samples harvested; 6 ran; 0 honoured the contract we drafted; 13 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 · our draft was wrong
4ran
13unverified

Licence: 0 of the 19 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 gabrielraya/symmetry_breaking_diffusion_models. “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_init gabrielraya/symmetry_breaking_diffusion_models/models/layers.py official repository ran MIT (permissive) · 04548c6c9fff2b3f · report
get_data_inverse_scaler gabrielraya/symmetry_breaking_diffusion_models/datasets.py official repository ran · our draft was wrong MIT (permissive) · 6c419026e778dee2 · report
get_data_scaler gabrielraya/symmetry_breaking_diffusion_models/datasets.py official repository ran · our draft was wrong MIT (permissive) · 346d2e6cc8b48a5d · report
get_optimizer gabrielraya/symmetry_breaking_diffusion_models/losses.py official repository ran MIT (permissive) · 8ff7c24dade9904c · report
optimization_manager gabrielraya/symmetry_breaking_diffusion_models/losses.py official repository ran MIT (permissive) · 366bb8c7035a2fc8 · report
variance_scaling gabrielraya/symmetry_breaking_diffusion_models/models/layers.py official repository ran MIT (permissive) · f34882fce4b22d20 · report
create_model gabrielraya/symmetry_breaking_diffusion_models/models/utils.py official repository unverified MIT (permissive) · c4dd4187aa1e3c9d · report
crop_resize gabrielraya/symmetry_breaking_diffusion_models/datasets.py official repository unverified MIT (permissive) · fd14d238ccd5f679 · report
func gabrielraya/symmetry_breaking_diffusion_models/diversity_eval.py official repository unverified MIT (permissive) · 899b121e3d100946 · report
generate_xt_samples gabrielraya/symmetry_breaking_diffusion_models/fast_sampler.py official repository unverified MIT (permissive) · 6a23f5f1484e38c8 · report
get_act gabrielraya/symmetry_breaking_diffusion_models/models/layers.py official repository unverified MIT (permissive) · 8232012f278d45f4 · report
get_approx_stats gabrielraya/symmetry_breaking_diffusion_models/fast_sampler.py official repository unverified MIT (permissive) · bec27c2f10409e37 · report
get_approx_stats_HQ gabrielraya/symmetry_breaking_diffusion_models/fast_sampler.py official repository unverified MIT (permissive) · f394c103783c55c8 · report
get_batch_activations gabrielraya/symmetry_breaking_diffusion_models/fast_fid.py official repository unverified MIT (permissive) · ecef6cc47991aad2 · report
get_batch_stats gabrielraya/symmetry_breaking_diffusion_models/fast_fid.py official repository unverified MIT (permissive) · 2cd0e1616c274ce4 · report
get_data_stats gabrielraya/symmetry_breaking_diffusion_models/fast_fid.py official repository unverified MIT (permissive) · 441bd52748d62295 · report
get_model gabrielraya/symmetry_breaking_diffusion_models/models/utils.py official repository unverified MIT (permissive) · b3e18524b8df81a1 · report
load_dataset_stats gabrielraya/symmetry_breaking_diffusion_models/evaluation.py official repository unverified MIT (permissive) · 72cc7337a59b2a93 · report
register_model gabrielraya/symmetry_breaking_diffusion_models/models/utils.py official repository unverified MIT (permissive) · 79fcc0f38b056e86 · report

Tasks

Diversity

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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