SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.02707 · EMNLP · 2020

Sub-Instruction Aware Vision-and-Language Navigation

Qi Wu, Stephen Gould, Yicong Hong, Cristian Rodriguez-Opazo

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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; 0 no recorded run), measured 2026-11-21; 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/2004.02707.json · badge: /api/ran/2004.02707.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
YicongHong/Fine-Grained-R2R marked official in Papers with Code
Papers with Code archive
2 ran · 0 no recorded run
FunctionStatusWhere it lives
check_lemma Ran
ran; our contract draft was wrong, not the code
YicongHong/Fine-Grained-R2R/source/chunking_function.py
code served (permissive licence) · get_code("fd4e4d97b73c90f2")
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.

class Word:
    def __init__(self, text, lemma):
        self.text = text
        self.lemma = lemma

word_left = Word(text='left', lemma='leave')
word_your = Word(text='your', lemma='your')
word_other = Word(text='running', lemma='run')

ARGS = {
    'word': word_other
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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
create_chunk Ran
ran; our contract draft was wrong, not the code
YicongHong/Fine-Grained-R2R/source/chunking_function.py
code served (permissive licence) · get_code("8f2ee6387d2fc4b3")
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) and returned list. 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.

class Word:
    def __init__(self, index, text, lemma, dependency_relation, governor):
        self.index = index
        self.text = text
        self.lemma = lemma
        self.dependency_relation = dependency_relation
        self.governor = governor

class Sentence:
    def __init__(self, words):
        self.words = words

class Doc:
    def __init__(self, sentences):
        self.sentences = sentences

# Create a simple document with sentences and words
word1 = Word(index=1, text="turn", lemma="turn", dependency_relation="root", governor=0)
word2 = Word(index=2, text="left", lemma="left", dependency_relation="advmod", governor=1)
word3 = Word(index=3, text="and", lemma="and", dependency_relation="cc", governor=4)
word4 = Word(index=4, text="go", lemma="go", dependency_relation="conj", governor=1)
word5 = Word(index=5, text=".", lemma=".", dependency_relation="punct", governor=1)

sent1 = Sentence(words=[word1, word2, word3, word4, word5])

word6 = Word(index=1, text="then", lemma="then", dependency_relation="advmod", governor=2)
word7 = Word(index=2, text="stop", lemma="stop", dependency_relation="root", governor=0)
word8 = Word(index=3, text=".", lemma=".", dependency_relation="punct", governor=2)

sent2 = Sentence(words=[word6, word7, word8])

doc = Doc(sentences=[sent1, sent2])

ARGS = {
    "doc": doc
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list 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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 2 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 2026-11-21.

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 requires an agent to navigate through a real 3D environment following natural language instructions. Despite significant advances, few previous works are able to fully utilize the strong correspondence between the visual and textual sequences. Meanwhile, due to the lack of intermediate supervision, the agent's performance at following each part of the instruction cannot be assessed during navigation. In this work, we focus on the granularity of the visual and language sequences as well as the traceability of agents through the completion of an instruction. We provide agents with fine-grained annotations during training and find that they are able to follow the instruction better and have a higher chance of reaching the target at test time. We enrich the benchmark dataset Roomto-Room (R2R) with sub-instructions and their corresponding paths. To make use of this data, we propose effective sub-instruction attention and shifting modules that select and attend to a single sub-instruction at each time-step. We implement our sub-instruction modules in four state-of-the-art agents, compare with their baseline models, and show that our proposed method improves the performance of all four agents. We release the Fine-Grained R2R dataset (FGR2R) and the code at https://github. com/YicongHong/Fine-Grained-R2R.

For agents

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

get_harvested_code_for_paper("2004.02707")
get_code_for_paper("2004.02707")
have("2004.02707")

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

curl https://syntology.ai/api/ran/2004.02707.json

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

[![Syntology run record](https://syntology.ai/api/ran/2004.02707.svg)](https://syntology.ai/paper/2004.02707)

Connect an agent — have() is free.