SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2411.06503 · ICML · 2025

Diffusion Sampling Correction via Approximately 10 Parameters

Guangyi Wang, Yuren Cai, Lijiang Li, Wei Peng, Songzhi Su, Wenyu Chen

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 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; 1 failure of our instrument; 1 no recorded run), measured 2026-11-22; 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/2411.06503.json · badge: /api/ran/2411.06503.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
onefly123/pas canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
onefly123/PAS marked official in Papers with Code
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
get_denoised Ran
ran; our contract draft was wrong, not the code
onefly123/pas/pas_solvers.py
code served (permissive licence) · get_code("3eed7631aeebeabc")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create a mock network with guidance_type attribute
class GuidanceNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.guidance_type = "classifier-free"
        self.linear = nn.Linear(4, 4)
    
    def forward(self, x, t, condition=None, unconditional_condition=None):
        # x: [batch, features], t: [batch], condition and unconditional_condition are optional
        return self.linear(x)

# Create a mock network without guidance_type attribute
class SimpleNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 4)
    
    def forward(self, x, t, class_labels=None):
        # x: [batch, features], t: [batch], class_labels optional
        return self.linear(x)

# Test with guidance_type network
net_with_guidance = GuidanceNet()
x = torch.randn(2, 4)  # batch_size=2, features=4
t = torch.randint(0, 1000, (2,))  # batch_size=2, timestep indices
condition = torch.randn(2, 3)  # batch_size=2, condition_dim=3
unconditional_condition = torch.randn(2, 3)  # batch_size=2, condition_dim=3
class_labels = None

ARGS = {
    "net": net_with_guidance,
    "x": x,
    "t": t,
    "class_labels": class_labels,
    "condition": condition,
    "unconditional_condition": unconditional_condition,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
PCA_process Not yet run
unverified (harvested, no recorded run)
onefly123/PAS/pca_utils/utils.py
code served (permissive licence) · get_code("7a95cc8476c56eff")
How it ran

no invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 1 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
get_denoised 5 other papers
3 dated earlier, 2 later · 2 only as an assembly brick
2206.00364 (2022-06)
Elucidating the Design Space of Diffusion-Based Generative Models
2312.00094 (2023-12)
Fast ODE-based Sampling for Diffusion Models in Around 5 Steps
2409.19681 (2024-09)
Simple and Fast Distillation of Diffusion Models
and 2 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

While powerful for generation, Diffusion Probabilistic Models (DPMs) face slow sampling challenges, for which various distillation-based methods have been proposed. However, they typically require significant additional training costs and model parameter storage, limiting their practicality. In this work, we propose PCA-based Adaptive Search (PAS), which optimizes existing solvers for DPMs with minimal additional costs. Specifically, we first employ PCA to obtain a few basis vectors to span the high-dimensional sampling space, which enables us to learn just a set of coordinates to correct the sampling direction; furthermore, based on the observation that the cumulative truncation error exhibits an "S"-shape, we design an adaptive search strategy that further enhances the sampling efficiency and reduces the number of stored parameters to approximately 10. Extensive experiments demonstrate that PAS can significantly enhance existing fast solvers in a plug-and-play manner with negligible costs. E.g., on CIFAR10, PAS optimizes DDIM's FID from 15.69 to 4.37 (NFE=10) using only 12 parameters and sub-minute training on a single A100 GPU. Code is available at https://github.com/onefly123/PAS.

For agents

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

get_harvested_code_for_paper("2411.06503")
get_code_for_paper("2411.06503")
have("2411.06503")

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

curl https://syntology.ai/api/ran/2411.06503.json

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

[![Syntology run record](https://syntology.ai/api/ran/2411.06503.svg)](https://syntology.ai/paper/2411.06503)

Connect an agent — have() is free.