SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.16728 · 2024

Improving Diffusion Models's Data-Corruption Resistance using Scheduled Pseudo-Huber Loss

arXiv · PDF · Open in the Atlas

Code that ran

4 of 9 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 5 no recorded run), 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/2403.16728.json · badge: /api/ran/2403.16728.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
kabachuha/SPHL-for-stable-diffusion canonical (classifier label)
classifier basis: census
4 ran · 5 no recorded run
FunctionStatusWhere it lives
arg_to_list Ran
ran; our contract draft was wrong, not the code
kabachuha/SPHL-for-stable-diffusion/clipsim.py
pointer only (licence: NONE) · get_code("5b500c1337c4db18")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kabachuha/SPHL-for-stable-diffusion 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.

collate_fn Ran
ran; our contract draft was wrong, not the code
kabachuha/SPHL-for-stable-diffusion/train_dreambooth_lora.py
pointer only (licence: NONE) · get_code("256040ccde7473f2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kabachuha/SPHL-for-stable-diffusion 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.

conditional_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
kabachuha/SPHL-for-stable-diffusion/diffusers_scripts/text_to_image/train_text_to_image.py
pointer only (licence: NONE) · get_code("b344fd961a91fb5b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kabachuha/SPHL-for-stable-diffusion 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.

determine_scheduler_type Ran
ran; our contract draft was wrong, not the code
kabachuha/SPHL-for-stable-diffusion/diffusers_scripts/dreambooth/train_dreambooth_lora_sdxl.py
pointer only (licence: NONE); the stored copy get_code serves, from yibozhong/lily, is pointer only (licence: NONE) · get_code("03e1c6795642a8db")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kabachuha/SPHL-for-stable-diffusion 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_outpath Not yet run
unverified (harvested, no recorded run)
kabachuha/SPHL-for-stable-diffusion/train_test_runner.py
pointer only (licence: NONE) · get_code("4b50013a09f2bd73")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kabachuha/SPHL-for-stable-diffusion 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.

get_samples_outpath Not yet run
unverified (harvested, no recorded run)
kabachuha/SPHL-for-stable-diffusion/train_test_runner.py
pointer only (licence: NONE) · get_code("76279bf6a5cd2728")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kabachuha/SPHL-for-stable-diffusion 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.

import_model_class_from_model_name_or_path Not yet run
unverified (harvested, no recorded run)
kabachuha/SPHL-for-stable-diffusion/train_dreambooth_lora.py
pointer only (licence: NONE); the stored copy get_code serves, from KU-VGI/APDM, is pointer only (licence: NONE) · get_code("0eb3e94e8635150e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kabachuha/SPHL-for-stable-diffusion 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.

launch Not yet run
unverified (harvested, no recorded run)
kabachuha/SPHL-for-stable-diffusion/bigprint.py
pointer only (licence: NONE) · get_code("d42636f926f08aa0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kabachuha/SPHL-for-stable-diffusion 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.

parse_args Not yet run
unverified (harvested, no recorded run)
kabachuha/SPHL-for-stable-diffusion/train_dreambooth_lora.py
pointer only (licence: NONE) · get_code("e7c647408dcf0307")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kabachuha/SPHL-for-stable-diffusion 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 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 3 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 3 later) and 6 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
import_model_class_from_model_name_or_path 13 other papers
5 dated earlier, 8 later
2305.19327 (2023-05)
Cones 2: Customizable Image Synthesis with Multiple Subjects
2307.06949 (2023-07)
HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Models
2311.18815 (2023-11)
IMMA: Immunizing text-to-image Models against Malicious Adaptation
and 10 more not named here
collate_fn 5 other papers
4 dated earlier, 1 later
2306.14435 (2023-06)
DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing
2311.18815 (2023-11)
IMMA: Immunizing text-to-image Models against Malicious Adaptation
2312.00084 (2023-12)
Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?
and 2 more not named here
determine_scheduler_type 2 other papers
2 later
2406.11909 (2024-06)
Mixture-of-Subspaces in Low-Rank Adaptation
2407.09946 (2024-07)
Low-Rank Interconnected Adaptation across Layers

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

Diffusion models are known to be vulnerable to outliers in training data. In this paper we study an alternative diffusion loss function, which can preserve the high quality of generated data like the original squared $L_{2}$ loss while at the same time being robust to outliers. We propose to use pseudo-Huber loss function with a time-dependent parameter to allow for the trade-off between robustness on the most vulnerable early reverse-diffusion steps and fine details restoration on the final steps. We show that pseudo-Huber loss with the time-dependent parameter exhibits better performance on corrupted datasets in both image and audio domains. In addition, the loss function we propose can potentially help diffusion models to resist dataset corruption while not requiring data filtering or purification compared to conventional training algorithms.

For agents

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

get_harvested_code_for_paper("2403.16728")
get_code_for_paper("2403.16728")
have("2403.16728")

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

curl https://syntology.ai/api/ran/2403.16728.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.16728.svg)](https://syntology.ai/paper/2403.16728)

Connect an agent — have() is free.