Papers › Unified Continuous Generative Models

Unified Continuous Generative Models

12 May 2025arXiv:2505.07447archive 2025-07-28

Peng Sun, Yi Jiang, Tao Lin

Recent advances in continuous generative models, including multi-step approaches like diffusion and flow-matching (typically requiring 8-1000 sampling steps) and few-step methods such as consistency models (typically 1-8 steps), have demonstrated impressive generative performance. However, existing work often treats these approaches as distinct paradigms, resulting in separate training and sampling methodologies. We introduce a unified framework for training, sampling, and analyzing these models. Our implementation, the Unified Continuous Generative Models Trainer and Sampler (UCGM-{T,S}), achieves state-of-the-art (SOTA) performance. For example, on ImageNet 256x256 using a 675M diffusion transformer, UCGM-T trains a multi-step model achieving 1.30 FID in 20 steps and a few-step model reaching 1.42 FID in just 2 steps. Additionally, applying UCGM-S to a pre-trained model (previously 1.26 FID at 250 steps) improves performance to 1.06 FID in only 40 steps. Code is available at: https://github.com/LINs-lab/UCGM.

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 21 code samples harvested from 1 repository linked to this paper: 19 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 1 violated, 3 with no contract checked; 12 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 9 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 21 samples from 1 repository, 19 ran (7 with no instrument failure; 12 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 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 5 of the 19 samples that ran have no recorded date.

LINs-Lab/UCGM officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 21 samples, 19 ran (12 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

21 samples harvested: 19 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 1 violated, 3 with no contract checked; 12 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.

3ran · honoured contract
1ran · violated contract
9ran · our draft was wrong
3ran; the contract check could not run
3ran
2unverified

Licence: 4 of the 21 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 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 LINs-Lab/UCGM. “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.

LINs-Lab/UCGM official repository 21 samples, 19 ran (12 instrument-failed) · 2 unverified
Normalize in 154 papers autoencs/autoencoder.py ran · our draft was wrong Apache-2.0 (permissive) · 9fcdaa6e423e8aa7 · report fixture: signature in_channels:int/0/int, num_groups:int/0/int · returned GroupNorm · level recorded 2026-09-22
apply_rotary_emb in 121 papers networks/rmsnorm.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant Apache-2.0 (permissive) · d7b6dcfe63bfe59b · report fixture: signature xq:Tensor/4/float, xk:Tensor/4/float, freqs_cis:Tensor/2/complex · returned tuple · level recorded 2026-09-22
apply_rotary_emb in 121 papers networks/ddt.py ran Apache-2.0 (permissive) · d0b336b17472a69b · report fixture: signature xq:Tensor/4/float, xk:Tensor/4/float, freqs_cis:Tensor/2/complex · returned tuple · level recorded 2026-09-25
broadcat in 21 papers networks/pos_embed.py ran · honoured contract Apache-2.0 (permissive) · f50a8d20efb35c68 · report fixture: signature tensors:list/1/Tensor, dim:int/0/int · returned Tensor · level recorded 2026-09-22
center_crop_arr in 79 papers autoencs/autoencoder.py ran · our draft was wrong Apache-2.0 (permissive) · 1712a07966b542ee · report fixture: signature pil_image:Image/0/?, image_size:int/0/int · returned Image · level recorded, date not recorded
const_like in 6 papers networks/edm2.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · f2514403e004d82b · report fixture: signature ref:Tensor/2/float, value:float/0/float, shape:tuple/1/int, dtype:dtype/0/?, device:device/0/?, memory_format:memory_format/0/? · returned Tensor · level recorded 2026-09-24
constant in 36 papers networks/edm2.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 6d32f9cf6f29b386 · report fixture: signature value:ndarray/1/float, shape:tuple/1/int, dtype:dtype/0/?, device:device/0/?, memory_format:memory_format/0/? · returned Tensor · level recorded 2026-09-24
get_2d_sincos_pos_embed in 170 papers networks/lightningdit.py ran · honoured contract Apache-2.0 (permissive) · c92c27c924b517e8 · report fixture: signature embed_dim:int/0/int, grid_size:int/0/int, cls_token:bool/0/bool, extra_tokens:int/0/int · returned ndarray · level recorded, date not recorded
get_attr_from_nested_module methodes/unigen.py ran Apache-2.0 (permissive) · f18f5056c31115fc · report fixture: signature model:callable/0/?, attr_name:str/0/str · returned str · level recorded 2026-09-25
mean_flat in 53 papers
census: 9 implementations from 18 papers, 4 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 2 of 3, arg 1: rank 4, kind float, dtype float32
methodes/unigen.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · dd96bc6c07c85dae · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
modulate in 137 papers
census: 3 implementations from 12 papers, 1 distinct output on one shared input
networks/sit.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 03310bba324ae4fb · report fixture: signature x:Tensor/2/float, shift:Tensor/1/float, scale:Tensor/1/float · returned Tensor · level recorded, date not recorded
modulate in 137 papers
census: 3 implementations from 12 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 · arg 3: rank 2, kind float, dtype float32
networks/ddt.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 62fcb3912a967a50 · report fixture: signature x:Tensor/2/float, shift:Tensor/2/float, scale:Tensor/2/float · returned Tensor · level recorded, date not recorded
nonlinearity in 140 papers
census: 4 implementations from 11 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
autoencs/autoencoder.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 3137073275f8c21a · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket
networks/edm2.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · ebfd171dc25ba0ce · report fixture: signature x:Tensor/2/float, dim:NoneType/0/?, eps:float/0/float · returned Tensor · level recorded 2026-09-24
precompute_freqs_cis in 112 papers networks/rmsnorm.py ran · violated contract Apache-2.0 (permissive) · 04a1fa63d6d4b8e4 · report fixture: signature dim:int/0/int, end:int/0/int, theta:float/0/float · returned Tensor · level recorded 2026-09-22
precompute_freqs_cis_2d in 13 papers networks/ddt.py ran Apache-2.0 (permissive) · 48b378bed8fc0083 · report fixture: signature dim:int/0/int, height:int/0/int, width:int/0/int, theta:float/0/float, scale:float/0/float · returned Tensor · level recorded 2026-09-25
reshape_for_broadcast in 90 papers
census: 6 implementations from 10 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 3, kind float, dtype float32
networks/rmsnorm.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 5a639d78ada17fee · report fixture: signature freqs_cis:Tensor/2/float, x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
rotate_half in 424 papers
census: 24 implementations from 96 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
networks/pos_embed.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 58823d9435a8751b · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
weight_init in 73 papers networks/unetplus.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · d41a4250066bce93 · report fixture: signature shape:tuple/1/int, mode:str/0/str, fan_in:int/0/int, fan_out:int/0/int · returned Tensor · level recorded 2026-09-22
get_2d_sincos_pos_embed_from_grid in 140 papers networks/lightningdit.py unverified Apache-2.0 (permissive) · 665d8a4e8f673a4c · report

Tasks

Image Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation ImageNet 256x256 SiT-XL/2 + UCGM-S (E2E-VAE + 40 sampling steps + CFG) FID 1.06 #1 of 94 Archive leaderboard report
Image Generation ImageNet 256x256 SiT-XL/2 + UCGM-S (E2E-VAE + 40 sampling steps + CFG) NFE 80 #1 of 94 Archive leaderboard report
Image Generation ImageNet 256x256 UCGM-XL/2 (VA-VAE + 30 sampling steps, without guidance) FID 1.21 #2 of 94 Archive leaderboard report
Image Generation ImageNet 256x256 UCGM-XL/2 (VA-VAE + 30 sampling steps, without guidance) NFE 30 #2 of 94 Archive leaderboard report
Image Generation ImageNet 256x256 UCGM-XL/2 (E2E-VAE + 40 sampling steps, without guidance) FID 1.21 #3 of 94 Archive leaderboard report
Image Generation ImageNet 256x256 UCGM-XL/2 (E2E-VAE + 40 sampling steps, without guidance) NFE 40 #3 of 94 Archive leaderboard report
Image Generation ImageNet 256x256 LightningDiT + UCGM-S (VA-VAE + 50 sampling steps + CFG) FID 1.21 #5 of 94 Archive leaderboard report
Image Generation ImageNet 256x256 LightningDiT + UCGM-S (VA-VAE + 50 sampling steps + CFG) NFE 100 #5 of 94 Archive leaderboard report
Image Generation ImageNet 512x512 DDT-XL/2 + UCGM-S (SD-VAE + 150 sampling steps + CFG) FID 1.24 #2 of 52 Archive leaderboard report
Image Generation ImageNet 512x512 DDT-XL/2 + UCGM-S (SD-VAE + 150 sampling steps + CFG) NFE 300 #2 of 52 Archive leaderboard report
Image Generation ImageNet 512x512 DDT-XL/2 + UCGM-S (SD-VAE + 100 sampling steps + CFG) FID 1.25 #3 of 52 Archive leaderboard report
Image Generation ImageNet 512x512 DDT-XL/2 + UCGM-S (SD-VAE + 100 sampling steps + CFG) NFE 200 #3 of 52 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

Consistency ModelsDiffusion

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