SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.03691 · ICML · 2022

Neural Implicit Dictionary Learning via Mixture-of-Expert Training

Tianlong Chen, Zhangyang Wang, Peihao Wang, Zhiwen Fan

arXiv · PDF · Open in the Atlas

Code that ran

6 of 15 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (6 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 0 failures of our instrument; 9 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/2207.03691.json · badge: /api/ran/2207.03691.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
vita-group/neural-implicit-dict canonical (classifier label)
classifier basis: classifier_2025
6 ran · 9 no recorded run
FunctionStatusWhere it lives
FCBlock Ran
ran on a synthesized input · constructed an object; no result was computed
vita-group/neural-implicit-dict/models.py
code served (permissive licence) · get_code("f756e1bf1683ec39")
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, through the batch API) and returned an instance of its own class, FCBlock: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type 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
import math
import numpy as np

torch.manual_seed(0)

ARGS = {
    'in_features': 4,
    'out_features': 3,
    'num_hidden_layers': 2,
    'hidden_features': 8,
    'outermost_linear': False,
    'nonlinearity': 'relu',
    'weight_init': None,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type FCBlock — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a FCBlock output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
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
FourierFeatMapping Ran
ran on a synthesized input · constructed an object; no result was computed
vita-group/neural-implicit-dict/models.py
code served (permissive licence) · get_code("590a7e6aebd2a441")
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, through the batch API) and returned an instance of its own class, FourierFeatMapping: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type 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)

# Define ARGS dict with all parameters for FourierFeatMapping.__init__
ARGS = {
    'in_dim': 4,
    'map_scale': 16,
    'map_size': 1024,
    'tunable': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type FourierFeatMapping — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a FourierFeatMapping output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
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
IdentityMapping Ran
ran on a synthesized input · constructed an object; no result was computed
vita-group/neural-implicit-dict/models.py
code served (permissive licence) · get_code("dfa297410a3da3e6")
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, through the batch API) and returned an instance of its own class, IdentityMapping: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type 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)

ARGS = {
    "in_dim": 4
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type IdentityMapping — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a IdentityMapping output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
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
PositionalEncoding Ran
ran on a synthesized input · constructed an object; no result was computed
vita-group/neural-implicit-dict/models.py
code served (permissive licence) · get_code("8c22d93e4d7f89e3")
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, through the batch API) and returned an instance of its own class, PositionalEncoding: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type 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
import math
import numpy as np

torch.manual_seed(0)

# Case 1: 3D input (in_features=3, num_frequencies will be auto-set to 10)
ARGS = {
    'in_features': 3,
    'num_frequencies': -1,
    'sidelength': None,
    'use_nyquist': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type PositionalEncoding — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a PositionalEncoding output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
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
RBFLayer Ran
ran on a synthesized input · constructed an object; no result was computed
vita-group/neural-implicit-dict/models.py
code served (permissive licence) · get_code("6049ee59a61d0375")
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, through the batch API) and returned an instance of its own class, RBFLayer: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type 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
import numpy as np

torch.manual_seed(0)

ARGS = {
    "in_features": 4,
    "out_features": 3,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type RBFLayer — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a RBFLayer output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
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
Sine Ran
ran on a synthesized input · constructed an object; no result was computed
vita-group/neural-implicit-dict/models.py
code served (permissive licence) · get_code("f725c8f70ba37716")
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, through the batch API) and returned an instance of its own class, Sine: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type 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)

class Sine(nn.Module):
    def __init__(self):
        super().__init__()

    def forward(self, input):
        return torch.sin(30 * input)

# Create a small input tensor (batch_size=2, features=4)
input_tensor = torch.randn(2, 4)

ARGS = {}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sine — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Sine output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
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
INRMoE Not yet run
unverified (harvested, no recorded run)
vita-group/neural-implicit-dict/models.py
code served (permissive licence) · get_code("b37256b41cf55cbd")
How it ran

no invocation recorded.

INRNet Not yet run
unverified (harvested, no recorded run)
vita-group/neural-implicit-dict/models.py
code served (permissive licence) · get_code("d64923580e745bc2")
How it ran

no invocation recorded.

MoECombiner Not yet run
unverified (harvested, no recorded run)
vita-group/neural-implicit-dict/models.py
code served (permissive licence) · get_code("ba9654f756e1e1f1")
How it ran

no invocation recorded.

RandomFourierMapping Not yet run
unverified (harvested, no recorded run)
vita-group/neural-implicit-dict/models.py
code served (permissive licence) · get_code("c91e5d7bfb64a8ee")
How it ran

no invocation recorded.

init_weights_elu Not yet run
unverified (harvested, no recorded run)
vita-group/neural-implicit-dict/models.py
code served (permissive licence) · get_code("c342d1c15dad9826")
How it ran

no invocation recorded.

init_weights_normal Not yet run
unverified (harvested, no recorded run)
vita-group/neural-implicit-dict/models.py
code served (permissive licence) · get_code("6b8816b6be7c9e2b")
How it ran

no invocation recorded.

init_weights_relu Not yet run
unverified (harvested, no recorded run)
vita-group/neural-implicit-dict/models.py
code served (permissive licence) · get_code("07ca9e05bd1b5378")
How it ran

no invocation recorded.

init_weights_selu Not yet run
unverified (harvested, no recorded run)
vita-group/neural-implicit-dict/models.py
code served (permissive licence) · get_code("5f4fed9f6dd565ef")
How it ran

no invocation recorded.

init_weights_xavier Not yet run
unverified (harvested, no recorded run)
vita-group/neural-implicit-dict/models.py
code served (permissive licence) · get_code("9d952dc991e7ac2e")
How it ran

no invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 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 14 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
Sine
brick of this paper's assembly: helper
2 other papers
1 dated earlier, 1 later · 1 only as an assembly brick
2006.09661 (2020-06)
Implicit Neural Representations with Periodic Activation Functions
2409.19472 (2024-09)
Towards Croppable Implicit Neural Representations

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

Representing visual signals by coordinate-based deep fully-connected networks has been shown advantageous in fitting complex details and solving inverse problems than discrete grid-based representation. However, acquiring such a continuous Implicit Neural Representation (INR) requires tedious per-scene training on tons of signal measurements, which limits its practicality. In this paper, we present a generic INR framework that achieves both data and training efficiency by learning a Neural Implicit Dictionary (NID) from a data collection and representing INR as a functional combination of basis sampled from the dictionary. Our NID assembles a group of coordinate-based subnetworks which are tuned to span the desired function space. After training, one can instantly and robustly acquire an unseen scene representation by solving the coding coefficients. To parallelly optimize a large group of networks, we borrow the idea from Mixture-of-Expert (MoE) to design and train our network with a sparse gating mechanism. Our experiments show that, NID can improve reconstruction of 2D images or 3D scenes by 2 orders of magnitude faster with up to 98% less input data. We further demonstrate various applications of NID in image inpainting and occlusion removal, which are considered to be challenging with vanilla INR. Our codes are available in https://github.com/VITA-Group/ Neural-Implicit-Dict.

For agents

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

get_harvested_code_for_paper("2207.03691")
get_code_for_paper("2207.03691")
have("2207.03691")

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

curl https://syntology.ai/api/ran/2207.03691.json

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

[![Syntology run record](https://syntology.ai/api/ran/2207.03691.svg)](https://syntology.ai/paper/2207.03691)

Connect an agent — have() is free.