SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2206.07699 · ICLR · 2023

Write and Paint: Generative Vision-Language Models are Unified Modal Learners

Wangchunshu Zhou, Xinsong Zhang, Shizhe Diao, Jiawei Wang

arXiv · PDF · Open in the Atlas

Code that ran

8 of 9 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; 4 failures of our instrument; 1 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/2206.07699.json · badge: /api/ran/2206.07699.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
shizhediao/davinci canonical (classifier label)
classifier basis not recorded on the link
8 ran · 1 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
shizhediao/davinci/image_linprobe.py
pointer only (licence: BSD-3-Clause) · get_code("131a82fd65128218")
How it ran

The body of this sample is withheld: BSD-3-Clause, as GitHub detects it on this paper's repository, shizhediao/davinci, 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.

adjust_learning_rate Ran
ran, honoured the contract we drafted
shizhediao/davinci/image_finetune.py
pointer only (licence: BSD-3-Clause); the stored copy get_code serves, from quandao10/slct, is pointer only (licence: NONE) · get_code("bd3578806ecf5ac2")
How it ran

The body of this sample is withheld: BSD-3-Clause, as GitHub detects it on this paper's repository, shizhediao/davinci, 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.

bpe_post_process Ran
ran on a synthesized input
shizhediao/davinci/eval_coco.py
pointer only (licence: BSD-3-Clause) · get_code("7cc42a822caf6361")
How it ran

The body of this sample is withheld: BSD-3-Clause, as GitHub detects it on this paper's repository, shizhediao/davinci, 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.

build_transform Ran
ran; our contract draft was wrong, not the code
shizhediao/davinci/image_finetune.py
pointer only (licence: BSD-3-Clause) · get_code("719b9682b050e2c1")
How it ran

The body of this sample is withheld: BSD-3-Clause, as GitHub detects it on this paper's repository, shizhediao/davinci, 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.

tile Ran
ran; our contract draft was wrong, not the code
shizhediao/davinci/models/davinci_pretrain.py
pointer only (licence: BSD-3-Clause); the stored copy get_code serves, from timmy-chan/miss, is pointer only (licence: NONE) · get_code("aa5a91226269bf75")
How it ran

The body of this sample is withheld: BSD-3-Clause, as GitHub detects it on this paper's repository, shizhediao/davinci, 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.

top_k_top_p_filtering Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
shizhediao/davinci/models/davinci_pretrain.py
pointer only (licence: BSD-3-Clause) · get_code("8164123ea94d7bb5")
How it ran

The body of this sample is withheld: BSD-3-Clause, as GitHub detects it on this paper's repository, shizhediao/davinci, 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.

validate Ran
ran on a synthesized input
shizhediao/davinci/image_finetune.py
pointer only (licence: BSD-3-Clause) · get_code("0a929b32383b0b8b")
How it ran

The body of this sample is withheld: BSD-3-Clause, as GitHub detects it on this paper's repository, shizhediao/davinci, 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.

validate Ran
ran on a synthesized input
shizhediao/davinci/image_linprobe.py
pointer only (licence: BSD-3-Clause) · get_code("b5ded0e5cccea0b1")
How it ran

The body of this sample is withheld: BSD-3-Clause, as GitHub detects it on this paper's repository, shizhediao/davinci, 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.

load_tf_weights_in_bert Not yet run
unverified (harvested, no recorded run)
shizhediao/davinci/models/bert.py
pointer only (licence: BSD-3-Clause) · get_code("4db905959447729d")
How it ran

The body of this sample is withheld: BSD-3-Clause, as GitHub detects it on this paper's repository, shizhediao/davinci, 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 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 6 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 1 the same month, 6 later) and 3 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
accuracy 116 other papers
44 dated earlier, 7 the same month, 61 later, 4 same year, order not determinable · 8 only as an assembly brick
1502.03044 (2015-02)
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
1610.05820 (2016-10)
Membership Inference Attacks Against Machine Learning Models
1905.03696 (2019-05)
HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision
and 113 more not named here
tile 84 other papers
84 later
2210.07795 (2022-10)
EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning
2210.08773 (2022-10)
Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training
2211.13594 (2022-11)
Self-supervised vision-language pretraining for Medical visual question answering
and 81 more not named here
adjust_learning_rate 23 other papers
2 dated earlier, 21 later
2105.12723 (2021-05)
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding
2204.09435 (2022-04)
Hephaestus: A large scale multitask dataset towards InSAR understanding
2212.00776 (2022-12)
ResFormer: Scaling ViTs with Multi-Resolution Training
and 20 more not named here
top_k_top_p_filtering 21 other papers
8 dated earlier, 13 later
1909.11942 (2019-09)
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
2005.00796 (2020-05)
A Simple Language Model for Task-Oriented Dialogue
2009.06367 (2020-09)
GeDi: Generative Discriminator Guided Sequence Generation
and 18 more not named here
build_transform 15 other papers
1 dated earlier, 14 later
2205.03892 (2022-05)
ConvMAE: Masked Convolution Meets Masked Autoencoders
2210.00788 (2022-10)
Towards a Unified View on Visual Parameter-Efficient Transfer Learning
2212.05677 (2022-12)
Masked autoencoders are effective solution to transformer data-hungry
and 12 more not named here
load_tf_weights_in_bert 14 other papers
1 dated earlier, 12 later, 1 same year, order not determinable
2112.02505 (2021-12)
Causal Distillation for Language Models
2022.findings-emnlp.24 (2022 (year only))
AssistSR: Task-oriented Video Segment Retrieval for Personal AI Assistant
2209.14279 (2022-09)
Causal Proxy Models for Concept-Based Model Explanations
and 11 more not named here

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

Recent advances in vision-language pre-training have pushed the state-of-the-art on various vision-language tasks, making machines more capable of multi-modal writing (image-to-text generation) and painting (text-to-image generation). However, few studies investigate if these two essential capabilities can be learned together and boost each other, making a versatile and powerful multi-modal foundation model. In this work, we disclose the potential of symmetric generative vision-language pre-training in learning to write and paint concurrently, and propose a new unified modal model, named DAVINCI, trained with prefix language modeling and prefix image modeling, a simple generative self-supervised objective on image-text pairs. Thanks to the proposed prefix multi-modal modeling framework, DAVINCI is simple to train, scalable to huge data, adaptable to both writing and painting tasks, and also strong on other vision, text, and multi-modal understanding tasks. DAVINCI achieves competitive performance on a wide range of 27 generation/understanding tasks and demonstrates the superiority of combining vision/language generative pre-training. Furthermore, we carefully benchmark the performance of different vision-language pre-training objectives on different scales of pre-training datasets on a heterogeneous and broad distribution coverage. Our results demonstrate the potential of exploiting self-supervision in both language and vision inputs, and establish new, stronger baselines for future comparisons at different data scales. 1

For agents

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

get_harvested_code_for_paper("2206.07699")
get_code_for_paper("2206.07699")
have("2206.07699")

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

curl https://syntology.ai/api/ran/2206.07699.json

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

[![Syntology run record](https://syntology.ai/api/ran/2206.07699.svg)](https://syntology.ai/paper/2206.07699)

Connect an agent — have() is free.