SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2105.06453 · ICCV · 2021

Episodic Transformer for Vision-and-Language Navigation

Cordelia Schmid, Chen Sun, Alexander Pashevich

arXiv · PDF · Open in the Atlas

Code that ran

2 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 0 have no contract verdict; 2 failures of our instrument; 4 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/2105.06453.json · badge: /api/ran/2105.06453.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
alexpashevich/E.T. canonical (classifier label)
classifier basis: census
2 ran · 4 no recorded run
FunctionStatusWhere it lives
compute_metrics Ran
ran; our contract draft was wrong, not the code
alexpashevich/E.T./alfred/eval/eval_subgoals.py
code served (permissive licence) · get_code("71f2661ddf223250")
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 sys

ARGS = {
    'subgoal_success': True,
    'subgoal_idx': 2,
    'reward': 0.85,
    'task': {
        'plan': {
            'low_actions': [
                {'high_idx': 2},
                {'high_idx': 2},
                {'high_idx': 2},
                {'high_idx': 1},
                {'high_idx': 1},
            ]
        }
    },
    't_agent': 5,
}
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 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
create_optimizer_and_schedulers Ran
ran; our contract draft was wrong, not the code
alexpashevich/E.T./alfred/utils/model_util.py
code served (permissive licence) · get_code("42214cbf20d06362")
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)

# Create a simple model with parameters
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

model = SimpleModel()
parameters = model.parameters()

# Create args dict with all required attributes
args = type('Args', (), {
    'lr': {
        'init': 0.001,
        'warmup_scale': 2.0,
        'warmup_epoch': 2,
        'profile': 'cosine',
        'decay_scale': 0.9,
        'decay_epoch': 5,
        'final': 0.0001,
        'cycle_epoch_up': 10,
        'cycle_epoch_down': 10,
    },
    'optimizer': 'adamw',
    'weight_decay': 0.01,
    'epochs': 20,
})()

ARGS = {
    'first_epoch': 0,
    'args': args,
    'parameters': parameters,
    'optimizer': None,
}
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
get_action Not yet run
unverified (harvested, no recorded run)
alexpashevich/E.T./alfred/env/reward.py
code served (permissive licence) · get_code("12ba53fedf724ead")
How it ran

no invocation recorded.

get_task Not yet run
unverified (harvested, no recorded run)
alexpashevich/E.T./alfred/env/tasks.py
code served (permissive licence) · get_code("d11401259503326f")
How it ran

no invocation recorded.

load_model Not yet run
unverified (harvested, no recorded run)
alexpashevich/E.T./alfred/utils/model_util.py
code served (permissive licence) · get_code("026a1fec14fca72d")
How it ran

no invocation recorded.

load_model_args Not yet run
unverified (harvested, no recorded run)
alexpashevich/E.T./alfred/utils/model_util.py
code served (permissive licence) · get_code("d34e3ef19764c321")
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, 4 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 4 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.

FunctionAlso present inEarliest-datedOthers named
get_action 5 other papers
1 dated earlier, 4 later
1912.01734 (2019-12)
ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks
2106.03427 (2021-06)
Hierarchical Task Learning from Language Instructions with Unified Transformers and Self-Monitoring
2308.09387 (2023-08)
Multi-Level Compositional Reasoning for Interactive Instruction Following
and 2 more not named here
get_task 1 other paper
1 later
2310.12344 (2023-10)
LACMA: Language-Aligning Contrastive Learning with Meta-Actions for Embodied Instruction Following
load_model 1 other paper
1 later
2310.12344 (2023-10)
LACMA: Language-Aligning Contrastive Learning with Meta-Actions for Embodied Instruction Following
load_model_args 1 other paper
1 later
2310.12344 (2023-10)
LACMA: Language-Aligning Contrastive Learning with Meta-Actions for Embodied Instruction Following

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

Interaction and navigation defined by natural language instructions in dynamic environments pose significant challenges for neural agents. This paper focuses on addressing two challenges: handling long sequence of subtasks, and understanding complex human instructions. We propose Episodic Transformer (E.T.), a multimodal transformer that encodes language inputs and the full episode history of visual observations and actions. To improve training, we leverage synthetic instructions as an intermediate representation that decouples understanding the visual appearance of an environment from the variations of natural language instructions. We demonstrate that encoding the history with a transformer is critical to solve compositional tasks, and that pretraining and joint training with synthetic instructions further improve the performance. Our approach sets a new state of the art on the challenging ALFRED benchmark, achieving 38.4% and 8.5% task success rates on seen and unseen test splits.

For agents

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

get_harvested_code_for_paper("2105.06453")
get_code_for_paper("2105.06453")
have("2105.06453")

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

curl https://syntology.ai/api/ran/2105.06453.json

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

[![Syntology run record](https://syntology.ai/api/ran/2105.06453.svg)](https://syntology.ai/paper/2105.06453)

Connect an agent — have() is free.