SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.02529 · ICML · 2024

ReLUs Are Sufficient for Learning Implicit Neural Representations

Robert Nowak, Joseph Shenouda, Yamin Zhou

arXiv · PDF · Open in the Atlas

Code that ran

5 of 7 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; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 2 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; 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/2406.02529.json · badge: /api/ran/2406.02529.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
joeshenouda/relu-inrs canonical (classifier label)
classifier basis: census
5 ran · 2 no recorded run
FunctionStatusWhere it lives
get_mgrid Ran
ran, honoured the contract we drafted
joeshenouda/relu-inrs/exp_audio_sig.py
pointer only (licence: NONE); the stored copy get_code serves, from GGorMM1/QIREN, is pointer only (licence: NONE) · get_code("6993cad8937592ca")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, joeshenouda/relu-inrs 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.

bspline_wavelet Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
joeshenouda/relu-inrs/modules/bspline_w.py
pointer only (licence: NONE) · get_code("393fa5aa9ed0cf1d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, joeshenouda/relu-inrs 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.

normalize Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
joeshenouda/relu-inrs/modules/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from Ali-Meh619/FKAN, is pointer only (licence: NONE) · get_code("432e64ee10a38168")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, joeshenouda/relu-inrs 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.

psnr Ran
ran, honoured the contract we drafted
joeshenouda/relu-inrs/modules/utils.py
pointer only (licence: NONE) · get_code("8fe08ad12dc74655")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, joeshenouda/relu-inrs 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.

rsnr Ran
ran, honoured the contract we drafted
joeshenouda/relu-inrs/modules/utils.py
pointer only (licence: NONE) · get_code("26862f3485c6ee4e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, joeshenouda/relu-inrs 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.

radon Not yet run
unverified (harvested, no recorded run)
joeshenouda/relu-inrs/modules/lin_inverse.py
pointer only (licence: NONE) · get_code("acc69a4fca2eab93")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, joeshenouda/relu-inrs 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.

train Not yet run
unverified (harvested, no recorded run)
joeshenouda/relu-inrs/exp_univariate_path_norms.py
pointer only (licence: NONE) · get_code("99ff1691eba94bb2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, joeshenouda/relu-inrs 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 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 1 the same month, 1 later) and 4 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_mgrid 3 other papers
2 dated earlier, 1 the same month
2007.02798 (2020-07)
Gradient Origin Networks
2007.09601 (2020-07)
Hypersolvers: Toward Fast Continuous-Depth Models
2406.03873 (2024-06)
Quantum Implicit Neural Representations
normalize 2 other papers
1 dated earlier, 1 later
2310.18846 (2023-10)
INCODE: Implicit Neural Conditioning with Prior Knowledge Embeddings
2409.09323 (2024-09)
Implicit Neural Representations with Fourier Kolmogorov-Arnold Networks
radon 1 other paper
1 dated earlier
2310.18846 (2023-10)
INCODE: Implicit Neural Conditioning with Prior Knowledge Embeddings

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

Motivated by the growing theoretical understanding of neural networks that employ the Rectified Linear Unit (ReLU) as their activation function, we revisit the use of ReLU activation functions for learning implicit neural representations (INRs). Inspired by second order B-spline wavelets, we incorporate a set of simple constraints to the ReLU neurons in each layer of a deep neural network (DNN) to remedy the spectral bias. This in turn enables its use for various INR tasks. Empirically, we demonstrate that, contrary to popular belief, one can learn state-of-the-art INRs based on a DNN composed of only ReLU neurons. Next, by leveraging recent theoretical works which characterize the kinds of functions ReLU neural networks learn, we provide a way to quantify the regularity of the learned function. This offers a principled approach to selecting the hyperparameters in INR architectures. We substantiate our claims through experiments in signal representation, super resolution, and computed tomography, demonstrating the versatility and effectiveness of our method. The code for all experiments can be found at https://github.com/joeshenouda/relu-inrs.

For agents

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

get_harvested_code_for_paper("2406.02529")
get_code_for_paper("2406.02529")
have("2406.02529")

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

curl https://syntology.ai/api/ran/2406.02529.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.02529.svg)](https://syntology.ai/paper/2406.02529)

Connect an agent — have() is free.