SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.00704 · 2023

Muse: Text-To-Image Generation via Masked Generative Transformers

arXiv · PDF · Open in the Atlas

Code that ran

19 of 21 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; 2 honoured the contract we drafted, 5 violated it and 1 has no contract verdict; 11 failures of our instrument; 2 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/2301.00704.json · badge: /api/ran/2301.00704.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
copy not recorded community
not in the paper's declared repositories
7 ran · 0 no recorded run
lucidrains/muse-pytorch community (classifier label)
classifier basis not recorded on the link
6 ran · 2 no recorded run
baaivision/muse-pytorch reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
Qiyuan-Ge/PaintMind reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
huggingface/amused reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
identity Ran
ran, honoured the contract we drafted
lucidrains/muse-pytorch/muse_maskgit_pytorch/trainers.py
code served (permissive licence) · get_code("7f1040f5e3991d5e")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-05T00:37:21Z). If your copy returns the same type, ndim and shape 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)

# The identity function simply returns its first argument
# and ignores all other args and kwargs
# So we need to provide a value for t and can optionally provide other args/kwargs

t = torch.randn(2, 4)
extra_arg_1 = torch.randn(3, 5)
extra_arg_2 = "some_string"
extra_kwarg_1 = 42
extra_kwarg_2 = [1, 2, 3]

ARGS = {
    "t": t,
    "args": (extra_arg_1, extra_arg_2),
    "kwargs": {"key1": extra_kwarg_1, "key2": extra_kwarg_2}
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
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
LSimple Ran
ran; our contract draft was wrong, not the code
baaivision/muse-pytorch/train_t2i_discrete_muse.py
code served (permissive licence) · get_code("35a0e57cdda9e212")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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)

class StandInSchedule:
    def sample(self, x0):
        batch_size, seq_len = x0.shape
        # Return labels and masked_ids
        # labels: which tokens were masked (batch_size, seq_len)
        # masked_ids: input with some tokens masked (batch_size, seq_len)
        labels = x0.clone()
        masked_ids = x0.clone()
        # Mask some positions (e.g., set to a special mask token id)
        mask_positions = torch.randint(0, seq_len, (batch_size, 1))
        for i in range(batch_size):
            masked_ids[i, mask_positions[i]] = 0  # 0 as mask token
        return labels, masked_ids
    
    def loss(self, logits, labels):
        # logits: (batch_size, seq_len, vocab_size)
        # labels: (batch_size, seq_len)
        batch_size, seq_len, vocab_size = logits.shape
        logits_flat = logits.view(-1, vocab_size)
        labels_flat = labels.view(-1)
        loss = nn.functional.cross_entropy(logits_flat, labels_flat)
        return loss

class StandInNNet(nn.Module):
    def __init__(self, vocab_size=10, hidden_dim=8, seq_len=5):
        super().__init__()
        self.embedding = nn.Embedding(vocab_size, hidden_dim)
        self.fc = nn.Linear(hidden_dim, vocab_size)
        self.seq_len = seq_len
    
    def forward(self, masked_ids, **kwargs):
        # masked_ids: (batch_size, seq_len)
        # Return logits: (batch_size, seq_len, vocab_size)
        embedded = self.embedding(masked_ids)  # (batch_size, seq_len, hidden_dim)
        logits = self.fc(embedded)  # (batch_size, seq_len, vocab_size)
        return logits

# Create inputs
batch_size = 2
seq_len = 5
vocab_size = 10

x0 = torch.randint(0, vocab_size, (batch_size, seq_len))
nnet = StandInNNet(vocab_size=vocab_size, hidden_dim=8, seq_len=seq_len)
schedule = StandInSchedule()

ARGS = {
    'x0': x0,
    'nnet': nnet,
    'schedule': schedule
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
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
add_gumbel_noise Ran
ran; our contract draft was wrong, not the code
baaivision/muse-pytorch/libs/muse.py
code served (permissive licence) · get_code("9ef9985f5609c318")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 numpy as np

torch.manual_seed(0)
np.random.seed(0)

t = torch.randn(2, 4)
temperature = 0.5
device = torch.device('cpu')

ARGS = {
    't': t,
    'temperature': temperature,
    'device': device
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
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
chunk Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from vicgalle/stable-diffusion-aesthetic-gradients
pointer only; the stored copy get_code serves, from vicgalle/stable-diffusion-aesthetic-gradients, is pointer only (licence: NOASSERTION) · get_code("8241c0562bc710fd")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for 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.

default Ran
ran, violated the contract we drafted
lucidrains/muse-pytorch/muse_maskgit_pytorch/muse_maskgit_pytorch.py
pointer only (licence: MIT); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("60fff7c3c400d7ff")
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.

default Ran
ran, violated the contract we drafted
Qiyuan-Ge/PaintMind/paintmind/generate.py
code served (permissive licence) · get_code("fbf9ec7be545688e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) 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.

import torch
import numpy as np
from inspect import isfunction

torch.manual_seed(0)

# Test case 1: val exists (not None), d is a regular value
val_case1 = 42
d_case1 = 100

# Test case 2: val is None, d is a regular value
val_case2 = None
d_case2 = "default_string"

# Test case 3: val is None, d is a function
val_case3 = None
def d_case3():
    return [1, 2, 3]

# Test case 4: val exists, d is a function (function should not be called)
val_case4 = torch.tensor([1.0, 2.0, 3.0])
def d_case4():
    return torch.tensor([4.0, 5.0, 6.0])

# We'll use case 2 for the main ARGS
ARGS = {
    'val': None,
    'd': "default_value"
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy, torch — 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
encode_prompt Ran
ran; our contract draft was wrong, not the code
huggingface/amused/training/train_amused.py
pointer only (licence: NONE) · get_code("af6cdb4b6a4b5860")
How it ran

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

eval_decorator Ran
ran; our contract draft was wrong, not the code
lucidrains/muse-pytorch/muse_maskgit_pytorch/muse_maskgit_pytorch.py
code served (permissive licence) · get_code("c16aee9490eb8729")
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 function. 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

torch.manual_seed(0)

# Build a minimal model that has .training attribute and .eval()/.train() methods
class MinimalModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Create model instance
model = MinimalModel()

# Define a simple function to decorate
def dummy_eval_fn(model, x):
    return model(x)

# The eval_decorator takes a function as its only parameter
ARGS = {
    "fn": dummy_eval_fn
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
lucidrains/muse-pytorch/muse_maskgit_pytorch/attend.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.

exists Ran
ran, violated the contract we drafted
this paper's copy was not recorded; identical code first harvested from lucidrains/bit-diffusion
pointer only · get_code("608e364a9d2376a3")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for 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.

find_index Ran
ran on a synthesized input
lucidrains/muse-pytorch/muse_maskgit_pytorch/trainers.py
code served (permissive licence) · get_code("3474c6be94998255")
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 int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 numpy as np

torch.manual_seed(0)

# The function find_index takes:
# 1. arr: an iterable to search through
# 2. cond: a callable that takes an element and returns a boolean

# Create a simple array (list of integers)
arr = [10, 20, 30, 40, 50]

# Create a condition function that checks if an element is greater than 25
cond = lambda x: x > 25

ARGS = {
    "arr": arr,
    "cond": cond
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, shape () — shape () as a later run recorded it
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
flatten_omega_conf Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from liusulin/DDPD
pointer only · get_code("ef8d9a0b717d3cb0")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for 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.

make_attention_mask Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from huggingface/open-muse
pointer only · get_code("e88526ab8fc3ebc4")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for 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.

mask_schedule Ran
ran, violated the contract we drafted
Qiyuan-Ge/PaintMind/paintmind/generate.py
code served (permissive licence) · get_code("4fd2dac3028a4e1f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned float64, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 math
import numpy as np

# The function takes a single parameter 'ratio' which is used in a mathematical expression
# It appears to be a scalar value that gets multiplied by pi/2 and passed to cosine
# Typically this would be a value between 0 and 1 representing a ratio/fraction

ratio = 0.5

ARGS = {
    'ratio': ratio
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float, shape () — shape () as a later run recorded it
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
once Ran
ran; our contract draft was wrong, not the code
lucidrains/muse-pytorch/muse_maskgit_pytorch/attend.py
code served (permissive licence) · get_code("52e10a7d6b0fa036")
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 function. 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
from functools import wraps

def once(fn):
    called = False

    @wraps(fn)
    def inner(x):
        nonlocal called
        if called:
            return
        called = True
        return fn(x)
    return inner


def sample_function(x):
    """A simple function that the decorator will wrap."""
    return x * 2


ARGS = {
    "fn": sample_function
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
prob_mask_like Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from huggingface/open-muse
pointer only · get_code("162f6eae613812c6")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for 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.

soft_target_cross_entropy Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from huggingface/open-muse
pointer only · get_code("d8437c41cc2a860f")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for 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.

tokenize_prompt Ran
ran, honoured the contract we drafted
huggingface/amused/training/train_amused.py
pointer only (licence: NONE) · get_code("e63f8661cb0af2c8")
How it ran

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

uniform Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from huggingface/open-muse
pointer only · get_code("66e51521e0875290")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for 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_model Not yet run
unverified (harvested, no recorded run)
lucidrains/muse-pytorch/muse_maskgit_pytorch/t5.py
code served (permissive licence) · get_code("feff9391629f5643")
How it ran

no invocation recorded.

get_tokenizer Not yet run
unverified (harvested, no recorded run)
lucidrains/muse-pytorch/muse_maskgit_pytorch/t5.py
code served (permissive licence) · get_code("cbdf413e88112af9")
How it ran

no invocation recorded.

Also present in other papers' code

Of 21 samples lifted from this paper's linked repositories, 21 carry a function identity and 0 do not. Of the 21 distinct functions with an identity, 17 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 4 the same month, 17 later) and 4 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
138 dated earlier, 5 the same month, 337 later, 4 same year, order not determinable, 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
default 207 other papers
32 dated earlier, 2 the same month, 171 later, 2 same year, order not determinable · 41 only as an assembly brick
1711.11585 (2017-11)
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.08162 (2020-10)
SidechainNet: An All-Atom Protein Structure Dataset for Machine Learning
and 204 more not named here
default 163 other papers
68 dated earlier, 3 the same month, 90 later, 1 same year, order not determinable, 1 undated · 27 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1810.00825 (2018-10)
Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
1907.01470 (2019-07)
Augmenting Self-attention with Persistent Memory
and 160 more not named here
exists 144 other papers
26 dated earlier, 2 the same month, 115 later, 1 same year, order not determinable · 40 only as an assembly brick
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1711.11585 (2017-11)
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
and 141 more not named here
identity 54 other papers
9 dated earlier, 44 later, 1 same year, order not determinable · 11 only as an assembly brick
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1907.01470 (2019-07)
Augmenting Self-attention with Persistent Memory
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
and 51 more not named here
chunk 40 other papers
10 dated earlier, 30 later
2106.14490 (2021-06)
Making Images Real Again: A Comprehensive Survey on Deep Image Composition
2112.10752 (2021-12)
High-Resolution Image Synthesis with Latent Diffusion Models
2204.11824 (2022-04)
Semi-Parametric Neural Image Synthesis
and 37 more not named here
once 19 other papers
5 dated earlier, 14 later · 4 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2202.01855 (2022-02)
Self-Supervised Learning with Random-Projection Quantizer for Speech Recognition
2203.07852 (2022-03)
Block-Recurrent Transformers
and 16 more not named here
eval_decorator 11 other papers
4 dated earlier, 7 later
1907.05242 (2019-07)
Large Memory Layers with Product Keys
2107.11906 (2021-07)
H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences
2112.05682 (2021-12)
Self-attention Does Not Need $O(n^2)$ Memory
and 8 more not named here
add_gumbel_noise 3 other papers
3 later
Hertz_Style_Aligned_Image_Generation_via_Shared_Attention_CVPR_2024_paper (2024 (year only))
Style Aligned Image Generation via Shared Attention
2406.05478 (2024-06)
Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis
2411.06959 (2024-11)
ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis
flatten_omega_conf 3 other papers
3 later
2410.06264 (2024-10)
Think While You Generate: Discrete Diffusion with Planned Denoising
2410.13136 (2024-10)
Unlocking the Capabilities of Masked Generative Models for Image Synthesis via Self-Guidance
2505.23380 (2025-05)
UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning
get_tokenizer 2 other papers
2 later
2410.11758 (2024-10)
Latent Action Pretraining from Videos
2502.12154 (2025-02)
Diffusion Models without Classifier-free Guidance
make_attention_mask 2 other papers
2 later
2410.13136 (2024-10)
Unlocking the Capabilities of Masked Generative Models for Image Synthesis via Self-Guidance
2410.20366 (2024-10)
Rethinking Reconstruction-based Graph-Level Anomaly Detection: Limitations and a Simple Remedy
prob_mask_like 2 other papers
2 later
2410.13136 (2024-10)
Unlocking the Capabilities of Masked Generative Models for Image Synthesis via Self-Guidance
2410.20366 (2024-10)
Rethinking Reconstruction-based Graph-Level Anomaly Detection: Limitations and a Simple Remedy
soft_target_cross_entropy 2 other papers
2 later
2410.13136 (2024-10)
Unlocking the Capabilities of Masked Generative Models for Image Synthesis via Self-Guidance
2505.23380 (2025-05)
UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning
uniform 2 other papers
2 later
2410.13136 (2024-10)
Unlocking the Capabilities of Masked Generative Models for Image Synthesis via Self-Guidance
2410.20366 (2024-10)
Rethinking Reconstruction-based Graph-Level Anomaly Detection: Limitations and a Simple Remedy
LSimple 1 other paper
1 later
Hertz_Style_Aligned_Image_Generation_via_Shared_Attention_CVPR_2024_paper (2024 (year only))
Style Aligned Image Generation via Shared Attention
get_model 1 other paper
1 later
2410.11758 (2024-10)
Latent Action Pretraining from Videos

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

We present Muse, a text-to-image Transformer model that achieves state-of-the-art image generation performance while being significantly more efficient than diffusion or autoregressive models. Muse is trained on a masked modeling task in discrete token space: given the text embedding extracted from a pre-trained large language model (LLM), Muse is trained to predict randomly masked image tokens. Compared to pixel-space diffusion models, such as Imagen and DALL-E 2, Muse is significantly more efficient due to the use of discrete tokens and requiring fewer sampling iterations; compared to autoregressive models, such as Parti, Muse is more efficient due to the use of parallel decoding. The use of a pre-trained LLM enables fine-grained language understanding, translating to high-fidelity image generation and the understanding of visual concepts such as objects, their spatial relationships, pose, cardinality etc. Our 900M parameter model achieves a new SOTA on CC3M, with an FID score of 6.06. The Muse 3B parameter model achieves an FID of 7.88 on zero-shot COCO evaluation, along with a CLIP score of 0.32. Muse also directly enables a number of image editing applications without the need to fine-tune or invert the model: inpainting, outpainting, and mask-free editing. More results are available at https://muse-model.github.io

For agents

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

get_harvested_code_for_paper("2301.00704")
get_code_for_paper("2301.00704")
have("2301.00704")

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

curl https://syntology.ai/api/ran/2301.00704.json

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

[![Syntology run record](https://syntology.ai/api/ran/2301.00704.svg)](https://syntology.ai/paper/2301.00704)

Connect an agent — have() is free.