SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.10904 · ICLR · 2022

SimVLM: Simple Visual Language Model Pretraining with Weak Supervision

Adams Yu, Jiahui Yu, Yuan Cao, Yulia Tsvetkov, Zihang Dai, Zirui Wang

arXiv · PDF · Open in the Atlas

Code that ran

22 of 37 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (8 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 3 violated it and 11 have no contract verdict; 7 failures of our instrument; 15 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/2108.10904.json · badge: /api/ran/2108.10904.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
FerryHuang/SimVLM community
Papers with Code archive
14 ran · 14 no recorded run
yulong-XJTU/SimVLM community (classifier label)
classifier basis not recorded on the link
8 ran · 1 no recorded run
FunctionStatusWhere it lives
BottleneckBlock Ran
ran on a synthesized input · constructed an object; no result was computed
FerryHuang/SimVLM/simvlm/modeling_simvlm.py
pointer only (licence: NONE) · get_code("325812bbd82c157f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FerryHuang/SimVLM 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.

CNNBlockBase Ran
ran on a synthesized input · constructed an object; no result was computed
FerryHuang/SimVLM/simvlm/modeling_simvlm.py
pointer only (licence: NONE) · get_code("38a875bbe943570b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FerryHuang/SimVLM 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.

Conv2d Ran
ran on a synthesized input · constructed an object; no result was computed
FerryHuang/SimVLM/simvlm/modeling_simvlm.py
pointer only (licence: NONE) · get_code("15258dcfb20b4488")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FerryHuang/SimVLM 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.

FrozenBatchNorm2d Ran
ran on a synthesized input · constructed an object; no result was computed
FerryHuang/SimVLM/simvlm/modeling_simvlm.py
pointer only (licence: NONE) · get_code("af6a9f58115fe4d6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FerryHuang/SimVLM 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.

SimVLMAttention Ran
ran on a synthesized input · constructed an object; no result was computed
FerryHuang/SimVLM/simvlm/modeling_simvlm.py
pointer only (licence: NONE) · get_code("1150381a8d9193ec")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FerryHuang/SimVLM 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.

SimVLMConfig Ran
ran on a synthesized input · constructed an object; no result was computed
FerryHuang/SimVLM/simvlm/modeling_simvlm.py
pointer only (licence: NONE) · get_code("7bb4727aca21db84")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FerryHuang/SimVLM 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.

SimVLMEncoder Ran
ran on a synthesized input · constructed an object; no result was computed
FerryHuang/SimVLM/simvlm/modeling_simvlm.py
pointer only (licence: NONE) · get_code("71c5d4fa9540b172")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FerryHuang/SimVLM 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.

SimVLMIntermediate Ran
ran on a synthesized input · constructed an object; no result was computed
FerryHuang/SimVLM/simvlm/modeling_simvlm.py
pointer only (licence: NONE) · get_code("81921e47a333c79d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FerryHuang/SimVLM 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.

basic_clean Ran
ran; our contract draft was wrong, not the code
yulong-XJTU/SimVLM/model/tokenizer.py
pointer only (licence: MIT); the stored copy get_code serves, from ltpwy/MSCI, is pointer only (licence: NONE) · get_code("98f385d847636a3e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ltpwy/MSCI, 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_input Ran
ran, honoured the contract we drafted
FerryHuang/SimVLM/simvlm/modeling_simvlm.py
pointer only (licence: NONE) · get_code("f6f30fe91451a8e9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FerryHuang/SimVLM 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.

clone Ran
ran on a synthesized input
yulong-XJTU/SimVLM/model/SimVLM.py
code served (permissive licence) · get_code("f7592e6aa673ef9a")
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 ModuleList. 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 torch
import torch.nn as nn
import copy

torch.manual_seed(0)

# Create a simple module to clone
class SimpleModule(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
        self.relu = nn.ReLU()
    
    def forward(self, x):
        return self.relu(self.linear(x))

module = SimpleModule()
N = 5

ARGS = {
    "module": module,
    "N": N
}
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 ModuleList — a ModuleList output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ModuleList output the recorded ndim 1 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
encoder Ran
ran on a synthesized input
yulong-XJTU/SimVLM/model/torch_transformer.py
code served (permissive licence) · get_code("053efec6ba1e990f")
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 TransformerEncoder. 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 torch
import torch.nn as nn
from torch.nn import Module, MultiheadAttention, ModuleList, Dropout, Linear, LayerNorm
import copy
import torch.nn.functional as F

torch.manual_seed(0)

def _get_clones(module, N):
    return ModuleList([copy.deepcopy(module) for i in range(N)])

def _get_activation_fn(activation):
    if activation == 'relu':
        return F.relu
    elif activation == 'gelu':
        return F.gelu
    raise RuntimeError('activation should be relu/gelu, not {}'.format(activation))

class TransformerEncoderLayer(Module):
    def __init__(self, d_model, nhead, dim_feedforward=2048, dropout=0.1, activation='relu'):
        super(TransformerEncoderLayer, self).__init__()
        self.self_attn = MultiheadAttention(d_model, nhead, dropout=dropout)
        self.linear1 = Linear(d_model, dim_feedforward)
        self.dropout = Dropout(dropout)
        self.linear2 = Linear(dim_feedforward, d_model)
        self.norm1 = LayerNorm(d_model)
        self.norm2 = LayerNorm(d_model)
        self.dropout1 = Dropout(dropout)
        self.dropout2 = Dropout(dropout)
        self.activation = _get_activation_fn(activation)

    def forward(self, src, src_mask=None, src_key_padding_mask=None):
        src2 = self.self_attn(src, src, src, attn_mask=src_mask, key_padding_mask=src_key_padding_mask)[0]
        src = src + self.dropout1(src2)
        src = self.norm1(src)
        src2 = self.linear2(self.dropout(self.activation(self.linear1(src))))
        src = src + self.dropout2(src2)
        src = self.norm2(src)
        return src

class TransformerEncoder(Module):
    __constants__ = ['norm']

    def __init__(self, encoder_layer, num_layers, norm=None):
        super(TransformerEncoder, self).__init__()
        self.layers = _get_clones(encoder_layer, num_layers)
        self.num_layers = num_layers
        self.norm = norm

    def forward(self, src, mask=None, src_key_padding_mask=None):
        output = src
        for mod in self.layers:
            output = mod(output, src_mask=mask, src_key_padding_mask=src_key_padding_mask)
        if self.norm is not None:
            output = self.norm(output)
        return output

def encoder(d_model=512, nhead=8, depth=1, dim_feedforward=2048, dropout=0.1, activation='relu'):
    encoder_layer = TransformerEncoderLayer(d_model, nhead, dim_feedforward, dropout, activation)
    norm = LayerNorm(d_model)
    return TransformerEncoder(encoder_layer, depth, norm)

ARGS = {
    'd_model': 4,
    'nhead': 2,
    'depth': 1,
    'dim_feedforward': 8,
    'dropout': 0.1,
    'activation': 'relu'
}
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 TransformerEncoder — a TransformerEncoder output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a TransformerEncoder 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
exists Ran
ran, violated the contract we drafted
yulong-XJTU/SimVLM/train_simVLM.py
pointer only (licence: MIT); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("aa5486a3650902d8")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ThomasMrY/VCT, 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.

find_pruneable_heads_and_indices Ran
ran; our contract draft was wrong, not the code
FerryHuang/SimVLM/simvlm/modeling_simvlm.py
pointer only (licence: NONE) · get_code("a98857f046bfe3d9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FerryHuang/SimVLM 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.

generate_square_subsequent_mask Ran
ran, violated the contract we drafted
yulong-XJTU/SimVLM/model/SimVLM.py
pointer only (licence: MIT); the stored copy get_code serves, from facebookresearch/dpcap, is pointer only (licence: NOASSERTION) · get_code("32b567f5aaaa591d")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from facebookresearch/dpcap, and GitHub could not classify the licence of that repository (NOASSERTION). 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_norm Ran
ran; our contract draft was wrong, not the code
FerryHuang/SimVLM/simvlm/modeling_simvlm.py
pointer only (licence: NONE) · get_code("7934a70c6ec449cd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FerryHuang/SimVLM 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.

get_norm Ran
ran on a synthesized input
yulong-XJTU/SimVLM/model/resblock.py
code served (permissive licence) · get_code("3d914d6f21ea094c")
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 FrozenBatchNorm2d. 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 torch
import torch.nn as nn
from torch.nn.modules.batchnorm import BatchNorm2d, SyncBatchNorm

torch.manual_seed(0)

# Create test arguments for get_norm function
ARGS = {
    "norm": "FrozenBN",  # Testing with FrozenBN string
    "out_channels": 64
}

# Alternative test cases can be constructed like this:
# ARGS = {"norm": "BN", "out_channels": 32}
# ARGS = {"norm": "GN", "out_channels": 16}
# ARGS = {"norm": None, "out_channels": 8}
# ARGS = {"norm": lambda channels: nn.BatchNorm2d(channels), "out_channels": 128}
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 FrozenBatchNorm2d — a FrozenBatchNorm2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a FrozenBatchNorm2d 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
get_pairs Ran
ran; our contract draft was wrong, not the code
yulong-XJTU/SimVLM/model/tokenizer.py
code served (permissive licence) · get_code("b50994ad24f6d583")
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 set. 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 torch

def get_pairs(word):
    pairs = set()
    prev_char = word[0]
    for char in word[1:]:
        pairs.add((prev_char, char))
        prev_char = char
    return pairs

ARGS = {
    "word": "hello"
}
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 set — a set output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a set 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
pad_with_id Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
FerryHuang/SimVLM/simvlm/modeling_simvlm.py
pointer only (licence: NONE) · get_code("cddcbab01417b2c1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FerryHuang/SimVLM 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.

prune_linear_layer Ran
ran; our contract draft was wrong, not the code
FerryHuang/SimVLM/simvlm/modeling_simvlm.py
pointer only (licence: NONE) · get_code("52de2aaa15da0643")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FerryHuang/SimVLM 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.

subsequent_mask Ran
ran, violated the contract we drafted
FerryHuang/SimVLM/simvlm/modeling_simvlm.py
pointer only (licence: NONE) · get_code("a9e07bbdd8c03e94")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FerryHuang/SimVLM 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.

whitespace_clean Ran
ran; our contract draft was wrong, not the code
yulong-XJTU/SimVLM/model/tokenizer.py
pointer only (licence: MIT); the stored copy get_code serves, from ltpwy/MSCI, is pointer only (licence: NONE) · get_code("9542161e9640b858")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ltpwy/MSCI, 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.

ResBlock Not yet run
unverified (harvested, no recorded run)
FerryHuang/SimVLM/simvlm/modeling_simvlm.py
pointer only (licence: NONE) · get_code("cb7f9fd225d85d47")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FerryHuang/SimVLM 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. No invocation recorded.

SimVLMCrossAttention Not yet run
unverified (harvested, no recorded run)
FerryHuang/SimVLM/simvlm/modeling_simvlm.py
pointer only (licence: NONE) · get_code("0ac4351224f69633")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FerryHuang/SimVLM 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. No invocation recorded.

SimVLMDecoder Not yet run
unverified (harvested, no recorded run)
FerryHuang/SimVLM/simvlm/modeling_simvlm.py
pointer only (licence: NONE) · get_code("e21d8701f32d884a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FerryHuang/SimVLM 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. No invocation recorded.

SimVLMDecoderLayer Not yet run
unverified (harvested, no recorded run)
FerryHuang/SimVLM/simvlm/modeling_simvlm.py
pointer only (licence: NONE) · get_code("d5689e71173b58c7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FerryHuang/SimVLM 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. No invocation recorded.

SimVLMEmbeddings Not yet run
unverified (harvested, no recorded run)
FerryHuang/SimVLM/simvlm/modeling_simvlm.py
pointer only (licence: NONE) · get_code("5e83675c723559e7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FerryHuang/SimVLM 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. No invocation recorded.

SimVLMEncoderLayer Not yet run
unverified (harvested, no recorded run)
FerryHuang/SimVLM/simvlm/modeling_simvlm.py
pointer only (licence: NONE) · get_code("6560411928394c1b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FerryHuang/SimVLM 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. No invocation recorded.

SimVLMModel Not yet run
unverified (harvested, no recorded run)
FerryHuang/SimVLM/simvlm/modeling_simvlm.py
pointer only (licence: NONE) · get_code("aed65580e72ec1ea")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FerryHuang/SimVLM 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. No invocation recorded.

SimVLMOutput Not yet run
unverified (harvested, no recorded run)
FerryHuang/SimVLM/simvlm/modeling_simvlm.py
pointer only (licence: NONE) · get_code("bf481d655ef58d6c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FerryHuang/SimVLM 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. No invocation recorded.

SimVLMPatchEmbeddings Not yet run
unverified (harvested, no recorded run)
FerryHuang/SimVLM/simvlm/modeling_simvlm.py
pointer only (licence: NONE) · get_code("2a710d51d64808b5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FerryHuang/SimVLM 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. No invocation recorded.

SimVLMSelfAttention Not yet run
unverified (harvested, no recorded run)
FerryHuang/SimVLM/simvlm/modeling_simvlm.py
pointer only (licence: NONE) · get_code("e1e1e84518402f22")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FerryHuang/SimVLM 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. No invocation recorded.

SimVLMSelfOutput Not yet run
unverified (harvested, no recorded run)
FerryHuang/SimVLM/simvlm/modeling_simvlm.py
pointer only (licence: NONE) · get_code("679fbced2dad1b6f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FerryHuang/SimVLM 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. No invocation recorded.

SimVLMTextEmbeddings Not yet run
unverified (harvested, no recorded run)
FerryHuang/SimVLM/simvlm/modeling_simvlm.py
pointer only (licence: NONE) · get_code("3e24126396b28223")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FerryHuang/SimVLM 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. No invocation recorded.

SimVLMToLogits Not yet run
unverified (harvested, no recorded run)
FerryHuang/SimVLM/simvlm/modeling_simvlm.py
pointer only (licence: NONE) · get_code("bd7c399bd6fdf0f2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FerryHuang/SimVLM 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. No invocation recorded.

c2_msra_fill Not yet run
unverified (harvested, no recorded run)
FerryHuang/SimVLM/simvlm/modeling_simvlm.py
pointer only (licence: NONE) · get_code("a3a75620f09b426d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FerryHuang/SimVLM 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. No invocation recorded.

decoder Not yet run
unverified (harvested, no recorded run)
yulong-XJTU/SimVLM/model/torch_transformer.py
code served (permissive licence) · get_code("beb8f635f68b899d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 37 samples lifted from this paper's linked repositories, 37 carry a function identity and 0 do not. Of the 36 distinct functions with an identity, 9 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 1 the same month, 9 later) and 27 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
exists 486 other papers
60 dated earlier, 2 the same month, 422 later, 2 undated · 78 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1804.04637 (2018-04)
EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
and 483 more not named here
get_pairs 258 other papers
13 dated earlier, 244 later, 1 undated · 4 only as an assembly brick
1802.06474 (2018-02)
A Closed-form Solution to Photorealistic Image Stylization
1803.01128 (2018-03)
Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples
1809.00125 (2018-09)
Simple Fusion: Return of the Language Model
and 255 more not named here
whitespace_clean 231 other papers
2 dated earlier, 228 later, 1 undated · 4 only as an assembly brick
1901.07441 (2019-01)
PadChest: A large chest x-ray image dataset with multi-label annotated reports
2107.06383 (2021-07)
How Much Can CLIP Benefit Vision-and-Language Tasks?
2109.08472 (2021-09)
ActionCLIP: A New Paradigm for Video Action Recognition
and 228 more not named here
basic_clean 218 other papers
2 dated earlier, 215 later, 1 undated · 4 only as an assembly brick
1901.07441 (2019-01)
PadChest: A large chest x-ray image dataset with multi-label annotated reports
2107.06383 (2021-07)
How Much Can CLIP Benefit Vision-and-Language Tasks?
2109.08472 (2021-09)
ActionCLIP: A New Paradigm for Video Action Recognition
and 215 more not named here
find_pruneable_heads_and_indices
brick of this paper's assembly: helper
11 other papers
2 dated earlier, 8 later, 1 same year, order not determinable
2004.10964 (2020-04)
Don't Stop Pretraining: Adapt Language Models to Domains and Tasks
2021.emnlp-main.154 (2021 (year only))
Reconstruction Attack on Instance Encoding for Language Understanding
2104.08066 (2021-04)
Effect of Visual Extensions on Natural Language Understanding in Vision-and-Language Models
and 8 more not named here
prune_linear_layer
brick of this paper's assembly: helper
4 other papers
4 later
2110.00855 (2021-10)
SurvTRACE: Transformers for Survival Analysis with Competing Events
2023.acl-long.264 (2023 (year only))
Towards Robust Low-Resource Fine-Tuning with Multi-View Compressed Representations
2402.13040 (2024-02)
Text-Guided Molecule Generation with Diffusion Language Model
and 1 more not named here
Conv2d
brick of this paper's assembly: helper
1 other paper
1 later
2405.16273 (2024-05)
M 3 GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation
c2_msra_fill
brick of this paper's assembly: helper
1 other paper
1 later
2305.00666 (2023-05)
Part Aware Contrastive Learning for Self-Supervised Action Recognition
generate_square_subsequent_mask 1 other paper
1 later
2403.02506 (2024-03)
Differentially Private Representation Learning via Image Captioning

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

With recent progress in joint modeling of visual and textual representations, Vision-Language Pretraining (VLP) has achieved impressive performance on many multimodal downstream tasks. However, the requirement for expensive annotations including clean image captions and regional labels limits the scalability of existing approaches, and complicates the pretraining procedure with the introduction of multiple dataset-specific objectives. In this work, we relax these constraints and present a minimalist pretraining framework, named Simple Visual Language Model (SimVLM). Unlike prior work, SimVLM reduces the training complexity by exploiting large-scale weak supervision, and is trained end-to-end with a single prefix language modeling objective. Without utilizing extra data or task-specific customization, the resulting model significantly outperforms previous pretraining methods and achieves new state-of-the-art results on a wide range of discriminative and generative vision-language benchmarks, including VQA (+3.74% vqa-score), NLVR2 (+1.17% accuracy), SNLI-VE (+1.37% accuracy) and image captioning tasks (+10.1% average CIDEr score). Furthermore, we demonstrate that SimVLM acquires strong generalization and transfer ability, enabling zero-shot behavior including open-ended visual question answering and cross-modality transfer.

For agents

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

get_harvested_code_for_paper("2108.10904")
get_code_for_paper("2108.10904")
have("2108.10904")

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

curl https://syntology.ai/api/ran/2108.10904.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.10904.svg)](https://syntology.ai/paper/2108.10904)

Connect an agent — have() is free.