SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2502.01441 · ICLR · 2025

Improved Training Technique for Latent Consistency Models

Trung Le, Dimitris Metaxas, Di Liu, Quan Dao, Khanh Doan

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 failures of our instrument; 1 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2502.01441.json · badge: /api/ran/2502.01441.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
quandao10/slct canonical (classifier label)
classifier basis: classifier_2025
6 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
normal_kl Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
quandao10/slct/models/losses.py
pointer only (licence: NONE) · get_code("75cca24835775136")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, quandao10/slct when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

adjust_learning_rate Ran
ran, honoured the contract we drafted
quandao10/slct/train_cm_latent_repa.py
pointer only (licence: NONE) · get_code("bd3578806ecf5ac2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, quandao10/slct when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

approx_standard_normal_cdf Ran
ran; our contract draft was wrong, not the code
quandao10/slct/models/losses.py
pointer only (licence: NONE) · get_code("cfd76fd0d89574a4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, quandao10/slct when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

center_crop_arr Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from liusulin/DDPD
pointer only · get_code("1712a07966b542ee")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

discretized_gaussian_log_likelihood Ran
ran; our contract draft was wrong, not the code
quandao10/slct/models/losses.py
pointer only (licence: NONE) · get_code("cd33283d615fb3d7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, quandao10/slct when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

exp_decay_weight Ran
ran; our contract draft was wrong, not the code
quandao10/slct/models/karras_diffusion.py
pointer only (licence: NONE) · get_code("3d32915eed1b1d44")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, quandao10/slct when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_weightings Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
quandao10/slct/models/karras_diffusion.py
pointer only (licence: NONE) · get_code("b99b8334fa5b1bc7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, quandao10/slct when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

create_logger Not yet run
unverified (harvested, no recorded run)
quandao10/slct/train_cm_latent_repa.py
pointer only (licence: NONE) · get_code("8382f7e48cc8a309")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, quandao10/slct when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 4 the same month, 6 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
normal_kl 160 other papers
140 dated earlier, 2 the same month, 16 later, 2 same year, order not determinable · 19 only as an assembly brick
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
and 157 more not named here
approx_standard_normal_cdf 154 other papers
134 dated earlier, 2 the same month, 16 later, 2 same year, order not determinable · 17 only as an assembly brick
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
and 151 more not named here
discretized_gaussian_log_likelihood 128 other papers
111 dated earlier, 2 the same month, 13 later, 2 same year, order not determinable · 16 only as an assembly brick
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
and 125 more not named here
center_crop_arr 37 other papers
24 dated earlier, 2 the same month, 9 later, 2 same year, order not determinable
2211.17091 (2022-11)
Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models
2212.09748 (2022-12)
Scalable Diffusion Models with Transformers
2311.09257 (2023-11)
UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANs
and 34 more not named here
adjust_learning_rate 23 other papers
22 dated earlier, 1 later
2105.12723 (2021-05)
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding
2204.09435 (2022-04)
Hephaestus: A large scale multitask dataset towards InSAR understanding
2206.07699 (2022-06)
Write and Paint: Generative Vision-Language Models are Unified Modal Learners
and 20 more not named here
create_logger 14 other papers
11 dated earlier, 3 later
2212.09748 (2022-12)
Scalable Diffusion Models with Transformers
2405.20337 (2024-05)
OccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Driving
2406.01733 (2024-06)
Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching
and 11 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Consistency models are a new family of generative models capable of producing high-quality samples in either a single step or multiple steps. Recently, consistency models have demonstrated impressive performance, achieving results on par with diffusion models in the pixel space. However, the success of scaling consistency training to large-scale datasets, particularly for text-to-image and video generation tasks, is determined by performance in the latent space. In this work, we analyze the statistical differences between pixel and latent spaces, discovering that latent data often contains highly impulsive outliers, which significantly degrade the performance of iCT in the latent space. To address this, we replace Pseudo-Huber losses with Cauchy losses, effectively mitigating the impact of outliers. Additionally, we introduce a diffusion loss at early timesteps and employ optimal transport (OT) coupling to further enhance performance. Lastly, we introduce the adaptive scaling-c scheduler to manage the robust training process and adopt Non-scaling LayerNorm in the architecture to better capture the statistics of the features and reduce outlier impact. With these strategies, we successfully train latent consistency models capable of high-quality sampling with one or two steps, significantly narrowing the performance gap between latent consistency and diffusion models. The implementation is released here:

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2502.01441")
get_code_for_paper("2502.01441")
have("2502.01441")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2502.01441.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2502.01441.svg)](https://syntology.ai/paper/2502.01441)

Connect an agent — have() is free.