SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.04429 · 2022

LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 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 3 have no contract verdict; 0 failures of our instrument; 2 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/2207.04429.json · badge: /api/ran/2207.04429.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
blazejosinski/lm_nav canonical (classifier label)
classifier basis not recorded on the link
3 ran · 2 no recorded run
FunctionStatusWhere it lives
get_hdf5_leaf_names Ran
ran on a synthesized input
blazejosinski/lm_nav/lm_nav/utils.py
code served (permissive licence) · get_code("ed1426f2a4432b88")
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 h5py
import os
import tempfile

# Create a temporary HDF5 file for testing
temp_dir = tempfile.mkdtemp()
temp_hdf5_path = os.path.join(temp_dir, 'test.h5')

# Create a sample HDF5 file with nested structure
with h5py.File(temp_hdf5_path, 'w') as f:
    # Create some groups and datasets
    group1 = f.create_group('group1')
    group1.create_dataset('dataset1', data=[1, 2, 3])
    group1.create_dataset('dataset2', data=[4, 5, 6])
    
    group2 = f.create_group('group2')
    subgroup = group2.create_group('subgroup')
    subgroup.create_dataset('dataset3', data=[7, 8, 9])
    
    f.create_dataset('root_dataset', data=[10, 11, 12])

ARGS = {
    'node': temp_hdf5_path,
    'name': ''
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
h5py — 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
im2bytes Ran
ran on a synthesized input
blazejosinski/lm_nav/lm_nav/utils.py
code served (permissive licence) · get_code("112c2db62806094e")
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 bytes. 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 numpy as np
import io
import PIL.Image

# Create a valid 3D numpy array (height, width, channels)
# Values must be in range [0, 255] for uint8 conversion in PIL
arr_3d = np.random.randint(0, 256, size=(32, 48, 3), dtype=np.uint8)

# Create a valid 4D numpy array (batch, height, width, channels)
arr_4d = np.random.randint(0, 256, size=(2, 32, 48, 3), dtype=np.uint8)

ARGS = {
    'arrs': arr_3d,
    'format': 'jpg'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bytes — a bytes output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a bytes 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
remove_article Ran
ran on a synthesized input
blazejosinski/lm_nav/lm_nav/landmark_extraction.py
code served (permissive licence) · get_code("f584724aa6279142")
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 str. 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 numpy as np

def remove_article(string):
    article = ['a', 'an', 'the']
    words = string.split()
    none_articles = [w for w in words if w not in article]
    return ' '.join(none_articles)

ARGS = {
    'string': 'the quick brown fox jumps over a lazy dog'
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
bytes2im Not yet run
unverified (harvested, no recorded run)
blazejosinski/lm_nav/lm_nav/utils.py
code served (permissive licence) · get_code("f794c8e3220abf6a")
How it ran

no invocation recorded.

generic_language_model_api_call Not yet run
unverified (harvested, no recorded run)
blazejosinski/lm_nav/lm_nav/landmark_extraction.py
code served (permissive licence) · get_code("016e7731808ea841")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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 5 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

Goal-conditioned policies for robotic navigation can be trained on large, unannotated datasets, providing for good generalization to real-world settings. However, particularly in vision-based settings where specifying goals requires an image, this makes for an unnatural interface. Language provides a more convenient modality for communication with robots, but contemporary methods typically require expensive supervision, in the form of trajectories annotated with language descriptions. We present a system, LM-Nav, for robotic navigation that enjoys the benefits of training on unannotated large datasets of trajectories, while still providing a high-level interface to the user. Instead of utilizing a labeled instruction following dataset, we show that such a system can be constructed entirely out of pre-trained models for navigation (ViNG), image-language association (CLIP), and language modeling (GPT-3), without requiring any fine-tuning or language-annotated robot data. We instantiate LM-Nav on a real-world mobile robot and demonstrate long-horizon navigation through complex, outdoor environments from natural language instructions. For videos of our experiments, code release, and an interactive Colab notebook that runs in your browser, please check out our project page https://sites.google.com/view/lmnav

For agents

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

get_harvested_code_for_paper("2207.04429")
get_code_for_paper("2207.04429")
have("2207.04429")

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

curl https://syntology.ai/api/ran/2207.04429.json

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

[![Syntology run record](https://syntology.ai/api/ran/2207.04429.svg)](https://syntology.ai/paper/2207.04429)

Connect an agent — have() is free.