SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.14645 · 2026

Spectrum Matching: a Unified Perspective for Superior Diffusability in Latent Diffusion

K Leuven, Le Zhang, Matthew Blaschko, Mang Ning, Mingxiao Li, Albert Salah, Lanmiao Liu

arXiv · PDF · Open in the Atlas

Code that ran

8 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 failures of our instrument; 0 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/2603.14645.json · badge: /api/ran/2603.14645.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
forever208/SpectrumMatching community
Papers with Code archive
8 ran · 0 no recorded run
FunctionStatusWhere it lives
channel_agg_power_dct_unified Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
forever208/SpectrumMatching/utils_DCT.py
pointer only (licence: NONE) · get_code("f4f53e4511109408")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, forever208/SpectrumMatching 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.

dct_2d_torch_unified Ran
ran; our contract draft was wrong, not the code
forever208/SpectrumMatching/utils_DCT.py
pointer only (licence: NONE) · get_code("7d2f185f17a2d9e4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, forever208/SpectrumMatching 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.

downsample_to Ran
ran; our contract draft was wrong, not the code
forever208/SpectrumMatching/utils_DCT.py
pointer only (licence: NONE) · get_code("0ce482e54fcfdacb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, forever208/SpectrumMatching 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.

gaussian_blur Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
forever208/SpectrumMatching/utils_DCT.py
pointer only (licence: NONE) · get_code("b87f39d183e447a3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, forever208/SpectrumMatching 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.

gaussian_kernel2d Ran
ran, honoured the contract we drafted
forever208/SpectrumMatching/utils_DCT.py
pointer only (licence: NONE) · get_code("8717e6705ab72a31")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, forever208/SpectrumMatching 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.

latent_spectral_reg_dct Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
forever208/SpectrumMatching/utils_DCT.py
pointer only (licence: NONE) · get_code("d347e6d8127aac80")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, forever208/SpectrumMatching 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.

radial_band_energy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
forever208/SpectrumMatching/utils_DCT.py
pointer only (licence: NONE) · get_code("d92892e7d2e79a13")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, forever208/SpectrumMatching 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.

radial_bin_map Ran
ran, honoured the contract we drafted
forever208/SpectrumMatching/utils_DCT.py
pointer only (licence: NONE) · get_code("2f5d3e4973205c22")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, forever208/SpectrumMatching 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.

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, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 8 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.

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

In this paper, we study the diffusability (learnability) of variational autoencoders (VAE) in latent diffusion. First, we show that pixel-space diffusion trained with an MSE objective is inherently biased toward learning low and mid spatial frequencies, and that the power-law power spectral density (PSD) of natural images makes this bias perceptually beneficial. Motivated by this result, we propose the Spectrum Matching Hypothesis: latents with superior diffusability should (i) follow a flattened power-law PSD (Encoding Spectrum Matching, ESM) and (ii) preserve frequencyto-frequency semantic correspondence through the decoder (Decoding Spectrum Matching, DSM). In practice, we apply ESM by matching the PSD between images and latents, and DSM via shared spectral masking with frequency-aligned reconstruction. Importantly, Spectrum Matching provides a unified view that clarifies prior observations of over-noisy or over-smoothed latents, and interprets several recent methods as special cases (e.g., VA-VAE, EQ-VAE). Experiments suggest that Spectrum Matching yields superior diffusion generation on CelebA and ImageNet datasets, and outperforms prior approaches. Finally, we extend the spectral view to representation alignment (REPA): we show that the directional spectral energy of the target representation is crucial for REPA, and propose a DoG-based method to further improve the performance of REPA. Our code is available https://github.com/forever208/SpectrumMatching.

For agents

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

get_harvested_code_for_paper("2603.14645")
get_code_for_paper("2603.14645")
have("2603.14645")

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

curl https://syntology.ai/api/ran/2603.14645.json

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

[![Syntology run record](https://syntology.ai/api/ran/2603.14645.svg)](https://syntology.ai/paper/2603.14645)

Connect an agent — have() is free.