SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1909.11059 · 2019

Unified Vision-Language Pre-Training for Image Captioning and VQA

arXiv · PDF · Open in the Atlas

Code that ran

11 of 14 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; 1 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 7 failures of our instrument; 3 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/1909.11059.json · badge: /api/ran/1909.11059.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
LuoweiZhou/VLP canonical (classifier label)
classifier basis: census
11 ran · 3 no recorded run
FunctionStatusWhere it lives
swish Ran
ran; our contract draft was wrong, not the code
LuoweiZhou/VLP/pytorch_pretrained_bert/modeling.py
pointer only (licence: Apache-2.0) · get_code("0f786c407fb1ee4c")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, LuoweiZhou/VLP, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

array_to_str Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
LuoweiZhou/VLP/vlp/scst_utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from 98lingchen/MICCAI2026, is pointer only (licence: NONE) · get_code("cab04f1e2101c79a")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from 98lingchen/MICCAI2026, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

batch_list_to_batch_tensors Ran
ran on a synthesized input
LuoweiZhou/VLP/vlp/loader_utils.py
pointer only (licence: Apache-2.0) · get_code("7ff0d3834d30ddb5")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, LuoweiZhou/VLP, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

cached_path Ran
ran; our contract draft was wrong, not the code
LuoweiZhou/VLP/pytorch_pretrained_bert/file_utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from sejong-rcv/TAME, is pointer only (licence: NONE) · get_code("349d780dd4a89a37")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, LuoweiZhou/VLP, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

detokenize Ran
ran; our contract draft was wrong, not the code
LuoweiZhou/VLP/vlp/decode_img2txt.py
pointer only (licence: Apache-2.0) · get_code("633d1e424a09eb70")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, LuoweiZhou/VLP, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

filename_to_url Ran
ran; our contract draft was wrong, not the code
LuoweiZhou/VLP/pytorch_pretrained_bert/file_utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from sejong-rcv/TAME, is pointer only (licence: NONE) · get_code("db0ac56aaf6e35e6")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, LuoweiZhou/VLP, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

gelu Ran
ran, honoured the contract we drafted
LuoweiZhou/VLP/pytorch_pretrained_bert/modeling.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from shmsw25/qa-hard-em, is pointer only (licence: NONE) · get_code("40e9fee2e0b7e278")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, LuoweiZhou/VLP, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_random_word Ran
ran; our contract draft was wrong, not the code
LuoweiZhou/VLP/vlp/loader_utils.py
pointer only (licence: Apache-2.0) · get_code("0dc4252bed90db68")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, LuoweiZhou/VLP, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

to_contiguous Ran
ran on a synthesized input
LuoweiZhou/VLP/vlp/scst_utils.py
pointer only (licence: Apache-2.0) · get_code("df768a32f36d7728")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, LuoweiZhou/VLP, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

truncate_tokens_pair Ran
ran on a synthesized input
LuoweiZhou/VLP/vlp/seq2seq_loader.py
pointer only (licence: Apache-2.0) · get_code("900f8d4b7c3c4f40")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, LuoweiZhou/VLP, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

url_to_filename Ran
ran; our contract draft was wrong, not the code
LuoweiZhou/VLP/pytorch_pretrained_bert/file_utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from lonePatient/ERNIE-text-classification-pytorch, is pointer only (licence: NONE) · get_code("af64ec220e8bcdbc")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, LuoweiZhou/VLP, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

language_eval Not yet run
unverified (harvested, no recorded run)
LuoweiZhou/VLP/vlp/lang_utils.py
pointer only (licence: Apache-2.0) · get_code("c681ae13f540b4a3")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, LuoweiZhou/VLP, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

scatter_imbalance Not yet run
unverified (harvested, no recorded run)
LuoweiZhou/VLP/misc/data_parallel.py
pointer only (licence: Apache-2.0) · get_code("162a4118bd4b42b1")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, LuoweiZhou/VLP, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

scatter_kwargs_imbalance Not yet run
unverified (harvested, no recorded run)
LuoweiZhou/VLP/misc/data_parallel.py
pointer only (licence: Apache-2.0) · get_code("1f83e9eb8603cd57")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, LuoweiZhou/VLP, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 12 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 2 the same month, 12 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
swish 206 other papers
17 dated earlier, 4 the same month, 185 later · 44 only as an assembly brick
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1805.12114 (2018-05)
Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
1809.01357 (2018-09)
Zero Shot Learning for Code Education: Rubric Sampling with Deep Learning Inference
and 203 more not named here
gelu 198 other papers
18 dated earlier, 7 the same month, 173 later · 32 only as an assembly brick
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1901.10125 (2019-01)
Glyce: Glyph-vectors for Chinese Character Representations
and 195 more not named here
url_to_filename 20 other papers
3 dated earlier, 17 later · 3 only as an assembly brick
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1906.01698 (2019-06)
Open Sesame: Getting Inside BERT's Linguistic Knowledge
and 17 more not named here
cached_path 17 other papers
3 dated earlier, 14 later · 3 only as an assembly brick
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1906.01698 (2019-06)
Open Sesame: Getting Inside BERT's Linguistic Knowledge
and 14 more not named here
filename_to_url 13 other papers
2 dated earlier, 11 later
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1906.01698 (2019-06)
Open Sesame: Getting Inside BERT's Linguistic Knowledge
2109.00590 (2021-09)
WebQA: Multihop and Multimodal QA
and 10 more not named here
detokenize 4 other papers
4 later
2009.07032 (2020-09)
Noisy Self-Knowledge Distillation for Text Summarization
2021.findings-emnlp.347 (2021 (year only))
Attend, Memorize and Generate: Towards Faithful Table-to-Text Generation in Few Shots
aaai_21432 (2022 (year only))
DIALOGLM: Pre-trained Model for Long Dialogue Understanding and Summarization
and 1 more not named here
to_contiguous 3 other papers
1 dated earlier, 2 later
1804.09160 (2018-04)
No Metrics Are Perfect: Adversarial Reward Learning for Visual Storytelling
2110.09753 (2021-10)
Unifying Multimodal Transformer for Bi-directional Image and Text Generation
array_to_str 2 other papers
1 dated earlier, 1 later
1908.06954 (2019-08)
Attention on Attention for Image Captioning
2606.21447 (2026-06)
Precision Recall Controllable Radiology Report Generation via Hybrid Natural Language and Clinical Reward Learning
get_random_word 2 other papers
2 later
2021.findings-emnlp.347 (2021 (year only))
Attend, Memorize and Generate: Towards Faithful Table-to-Text Generation in Few Shots
2105.02605 (2021-05)
GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph
scatter_kwargs_imbalance 2 other papers
2 later
2021.findings-emnlp.347 (2021 (year only))
Attend, Memorize and Generate: Towards Faithful Table-to-Text Generation in Few Shots
2109.00590 (2021-09)
WebQA: Multihop and Multimodal QA
scatter_imbalance 1 other paper
1 later
2109.00590 (2021-09)
WebQA: Multihop and Multimodal QA
truncate_tokens_pair 1 other paper
1 later
2021.findings-emnlp.347 (2021 (year only))
Attend, Memorize and Generate: Towards Faithful Table-to-Text Generation in Few Shots

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

This paper presents a unified Vision-Language Pre-training (VLP) model. The model is unified in that (1) it can be fine-tuned for either vision-language generation (e.g., image captioning) or understanding (e.g., visual question answering) tasks, and (2) it uses a shared multi-layer transformer network for both encoding and decoding, which differs from many existing methods where the encoder and decoder are implemented using separate models. The unified VLP model is pre-trained on a large amount of image-text pairs using the unsupervised learning objectives of two tasks: bidirectional and sequence-to-sequence (seq2seq) masked vision-language prediction. The two tasks differ solely in what context the prediction conditions on. This is controlled by utilizing specific self-attention masks for the shared transformer network. To the best of our knowledge, VLP is the first reported model that achieves state-of-the-art results on both vision-language generation and understanding tasks, as disparate as image captioning and visual question answering, across three challenging benchmark datasets: COCO Captions, Flickr30k Captions, and VQA 2.0. The code and the pre-trained models are available at https://github.com/LuoweiZhou/VLP.

For agents

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

get_harvested_code_for_paper("1909.11059")
get_code_for_paper("1909.11059")
have("1909.11059")

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

curl https://syntology.ai/api/ran/1909.11059.json

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

[![Syntology run record](https://syntology.ai/api/ran/1909.11059.svg)](https://syntology.ai/paper/1909.11059)

Connect an agent — have() is free.