SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.05129 · 2022

Multi-Object Navigation with dynamically learned neural implicit representations

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 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 5 have no contract verdict; 0 failures of our instrument; 1 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/2210.05129.json · badge: /api/ran/2210.05129.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
PierreMarza/dynamic_implicit_representations canonical (classifier label)
classifier basis not recorded on the link
5 ran · 1 no recorded run
FunctionStatusWhere it lives
get_embedder Ran
ran on a synthesized input
PierreMarza/dynamic_implicit_representations/habitat_baselines/rl/models/implicit_representation.py
code served (permissive licence) · get_code("c0d4ae2a2ad451d8")
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 tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 = {
    'multires': 10,
    'i': 0
}
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 tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
q_conj Ran
ran on a synthesized input
PierreMarza/dynamic_implicit_representations/habitat_baselines/rl/models/implicit_projection.py
code served (permissive licence) · get_code("62c833d50f4c5339")
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 Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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

torch.manual_seed(0)

Q_TO_Q_CONJ = torch.Tensor([1, -1, -1, -1])

def q_conj(q):
    """
    Input        q: float tensor of size * x 4
    Output conj(q): float tensor of size * x 4
    """
    return q * Q_TO_Q_CONJ.to('cuda:0')

# Create a small quaternion tensor of shape (2, 4)
q_input = torch.randn(2, 4)

ARGS = {
    'q': q_input
}
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 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
q_prod Ran
ran on a synthesized input
PierreMarza/dynamic_implicit_representations/habitat_baselines/rl/models/implicit_projection.py
code served (permissive licence) · get_code("72e903b9851c9635")
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 Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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

torch.manual_seed(0)

# Create two quaternion tensors with batch size 2
# Each quaternion is represented as [w, x, y, z] (4 components)
q1 = torch.randn(2, 4)
q2 = torch.randn(2, 4)

ARGS = {
    "q1": q1,
    "q2": q2,
}
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 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
reading_net_expl_occ_weights Ran
ran on a synthesized input
PierreMarza/dynamic_implicit_representations/habitat_baselines/rl/models/implicit_representation_exploration_occupancy.py
code served (permissive licence) · get_code("49d17360d79ef1ca")
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 tuple. 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 SimpleNet(nn.Module):
    def __init__(self, input_dim=4, hidden_dim=3, output_dim=2):
        super().__init__()
        self.pts_linears = nn.Sequential(
            nn.Linear(input_dim, hidden_dim),
            nn.Linear(hidden_dim, hidden_dim)
        )
        self.out = nn.Linear(hidden_dim, output_dim)
    
    def forward(self, x):
        x = self.pts_linears(x)
        x = self.out(x)
        return x

# Create a list of networks for exploration
net1 = SimpleNet(input_dim=4, hidden_dim=3, output_dim=2)
net2 = SimpleNet(input_dim=4, hidden_dim=3, output_dim=2)

net_list_exploration = [net1, net2]
device = 'cpu'

ARGS = {
    'net_list_exploration': net_list_exploration,
    'device': device
}
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 tuple — a tuple output has no array shape of its own; none is 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
run_epoch_expl_occ Ran
ran on a synthesized input
PierreMarza/dynamic_implicit_representations/habitat_baselines/rl/models/implicit_representation_exploration_occupancy.py
code served (permissive licence) · get_code("1e45e5d13bfcf8de")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 simple network for explicit occupancy
class ExplOccNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.fc(x)

# Create criterion (loss function)
criterion = nn.CrossEntropyLoss()

# Create 2 networks (one per batch item)
net_expl_occ = [ExplOccNet(), ExplOccNet()]

# Create 2 optimizers (one per network)
optimizer_expl_occ = [
    torch.optim.SGD(net_expl_occ[0].parameters(), lr=0.01),
    torch.optim.SGD(net_expl_occ[1].parameters(), lr=0.01)
]

# Create input xyz data: batch_size=2, each item has shape (5, 4)
xyz = torch.randn(2, 5, 4)

# Create labels: batch_size=2, each item has shape (5,)
labels = torch.randint(0, 3, (2, 5))

# Create to_train flags: which items to train
to_train = [True, False]

ARGS = {
    "criterion": criterion,
    "net_expl_occ": net_expl_occ,
    "optimizer_expl_occ": optimizer_expl_occ,
    "xyz": xyz,
    "labels": labels,
    "to_train": to_train
}
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 list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
reproject Not yet run
unverified (harvested, no recorded run)
PierreMarza/dynamic_implicit_representations/habitat_baselines/rl/models/implicit_projection.py
code served (permissive licence) · get_code("45818bdef1634521")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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 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.

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

Understanding and mapping a new environment are core abilities of any autonomously navigating agent. While classical robotics usually estimates maps in a stand-alone manner with SLAM variants, which maintain a topological or metric representation, end-to-end learning of navigation keeps some form of memory in a neural network. Networks are typically imbued with inductive biases, which can range from vectorial representations to birds-eye metric tensors or topological structures. In this work, we propose to structure neural networks with two neural implicit representations, which are learned dynamically during each episode and map the content of the scene: (i) the Semantic Finder predicts the position of a previously seen queried object; (ii) the Occupancy and Exploration Implicit Representation encapsulates information about explored area and obstacles, and is queried with a novel global read mechanism which directly maps from function space to a usable embedding space. Both representations are leveraged by an agent trained with Reinforcement Learning (RL) and learned online during each episode. We evaluate the agent on Multi-Object Navigation and show the high impact of using neural implicit representations as a memory source.

For agents

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

get_harvested_code_for_paper("2210.05129")
get_code_for_paper("2210.05129")
have("2210.05129")

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

curl https://syntology.ai/api/ran/2210.05129.json

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

[![Syntology run record](https://syntology.ai/api/ran/2210.05129.svg)](https://syntology.ai/paper/2210.05129)

Connect an agent — have() is free.