SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.07201 · 2021

Neighbor-view Enhanced Model for Vision and Language Navigation

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 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 0 have no contract verdict; 2 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/2107.07201.json · badge: /api/ran/2107.07201.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
MarSaKi/NvEM canonical (classifier label)
classifier basis: census
2 ran · 2 no recorded run
FunctionStatusWhere it lives
compute_bleu Ran
ran; our contract draft was wrong, not the code
MarSaKi/NvEM/r2r_src/bleu.py
code served (permissive licence) · get_code("7b5b4685db18fbca")
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 collections
import math

# Set seed for reproducibility
import torch
torch.manual_seed(0)

# Create small example data for BLEU score computation
# reference_corpus: list of lists of references for each translation
# Each reference is a tokenized list
reference_corpus = [
    [['the', 'cat', 'sat', 'on', 'the', 'mat'],
     ['a', 'cat', 'was', 'sitting', 'on', 'the', 'mat']],
    [['hello', 'world'],
     ['hi', 'world']]
]

# translation_corpus: list of translations to score
# Each translation is a tokenized list
translation_corpus = [
    ['the', 'cat', 'sat', 'on', 'the', 'mat'],
    ['hello', 'world']
]

# max_order: maximum n-gram order
max_order = 4

# smooth: whether to apply smoothing
smooth = False

ARGS = {
    'reference_corpus': reference_corpus,
    'translation_corpus': translation_corpus,
    'max_order': max_order,
    'smooth': smooth
}
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
load_nav_graphs Ran
ran; our contract draft was wrong, not the code
MarSaKi/NvEM/r2r_src/utils.py
code served (permissive licence) · get_code("e3a90df1a875a38e")
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 dict. 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 json
import numpy as np
import networkx as nx
from unittest.mock import patch, mock_open
import tempfile
import os

# Create mock connectivity JSON data
mock_connectivity_data = [
    {
        'image_id': 'img_0',
        'included': True,
        'pose': [0, 0, 0, 1.0, 0, 0, 0, 2.0, 0, 0, 0, 3.0],
        'unobstructed': [True, True, False]
    },
    {
        'image_id': 'img_1',
        'included': True,
        'pose': [0, 0, 0, 1.5, 0, 0, 0, 2.5, 0, 0, 0, 3.5],
        'unobstructed': [True, True, False]
    },
    {
        'image_id': 'img_2',
        'included': False,
        'pose': [0, 0, 0, 2.0, 0, 0, 0, 3.0, 0, 0, 0, 4.0],
        'unobstructed': [False, False, True]
    }
]

# Create a temporary directory with mock connectivity files
temp_dir = tempfile.mkdtemp()
connectivity_dir = os.path.join(temp_dir, 'connectivity')
os.makedirs(connectivity_dir, exist_ok=True)

# Write mock connectivity files
for scan_name in ['scan_0', 'scan_1']:
    filepath = os.path.join(connectivity_dir, f'{scan_name}_connectivity.json')
    with open(filepath, 'w') as f:
        json.dump(mock_connectivity_data, f)

# Patch the file open to use our temp directory
original_open = open

def patched_open(file, *args, **kwargs):
    if 'connectivity/' in str(file):
        # Replace connectivity/ path with our temp directory path
        file = file.replace('connectivity/', connectivity_dir + '/')
    return original_open(file, *args, **kwargs)

# Apply the patch
import builtins
builtins.open = patched_open

ARGS = {
    'scans': ['scan_0', 'scan_1']
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
networkx, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
build_vocab Not yet run
unverified (harvested, no recorded run)
MarSaKi/NvEM/r2r_src/utils.py
code served (permissive licence) · get_code("de363b1cbf20852f")
How it ran

no invocation recorded.

load_datasets Not yet run
unverified (harvested, no recorded run)
MarSaKi/NvEM/r2r_src/utils.py
code served (permissive licence) · get_code("1d9c8c3cd78345c4")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 2 later) and 0 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
load_nav_graphs 7 other papers
5 dated earlier, 2 later
1901.03035 (2019-01)
Self-Monitoring Navigation Agent via Auxiliary Progress Estimation
1903.01602 (2019-03)
The Regretful Agent: Heuristic-Aided Navigation through Progress Estimation
1904.04195 (2019-04)
Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout
and 4 more not named here
compute_bleu 4 other papers
3 dated earlier, 1 later
1711.04090 (2017-11)
MojiTalk: Generating Emotional Responses at Scale
1904.04195 (2019-04)
Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout
2010.07954 (2020-10)
Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding
and 1 more not named here
build_vocab 3 other papers
3 dated earlier
1901.03035 (2019-01)
Self-Monitoring Navigation Agent via Auxiliary Progress Estimation
1903.01602 (2019-03)
The Regretful Agent: Heuristic-Aided Navigation through Progress Estimation
1904.04195 (2019-04)
Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout
load_datasets 1 other paper
1 dated earlier
1904.04195 (2019-04)
Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout

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

Vision and Language Navigation (VLN) requires an agent to navigate to a target location by following natural language instructions. Most of existing works represent a navigation candidate by the feature of the corresponding single view where the candidate lies in. However, an instruction may mention landmarks out of the single view as references, which might lead to failures of textual-visual matching of existing methods. In this work, we propose a multi-module Neighbor-View Enhanced Model (NvEM) to adaptively incorporate visual contexts from neighbor views for better textual-visual matching. Specifically, our NvEM utilizes a subject module and a reference module to collect contexts from neighbor views. The subject module fuses neighbor views at a global level, and the reference module fuses neighbor objects at a local level. Subjects and references are adaptively determined via attention me'chanisms. Our model also includes an action module to utilize the strong orientation guidance (e.g., "turn left") in instructions. Each module predicts navigation action separately and their weighted sum is used for predicting the final action. Extensive experimental results demonstrate the effectiveness of the proposed method on the R2R and R4R benchmarks against several state-of-the-art navigators, and NvEM even beats some pre-training ones. Our code is available at https://github.com/MarSaKi/NvEM.

For agents

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

get_harvested_code_for_paper("2107.07201")
get_code_for_paper("2107.07201")
have("2107.07201")

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

curl https://syntology.ai/api/ran/2107.07201.json

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

[![Syntology run record](https://syntology.ai/api/ran/2107.07201.svg)](https://syntology.ai/paper/2107.07201)

Connect an agent — have() is free.