SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.13136 · NeurIPS · 2024

Unlocking the Capabilities of Masked Generative Models for Image Synthesis via Self-Guidance

Korea, Junmo Kim, Gyojin Han, Jaehyun Choi, Jiwan Hur, Dong-Jae Lee, Yunho Jeon, South Kaist

arXiv · PDF · Open in the Atlas

Code that ran

11 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 11 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/2410.13136.json · badge: /api/ran/2410.13136.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
jiwanhur/unlockmgm canonical (classifier label)
classifier basis: census
7 ran · 1 no recorded run
huggingface/open-muse reimplementation (classifier label)
classifier basis: classifier_2025
4 ran · 0 no recorded run
FunctionStatusWhere it lives
flatten_omega_conf Ran
ran; our contract draft was wrong, not the code
jiwanhur/unlockmgm/training/train_maskgit_imagenet.py
pointer only (licence: NONE) · get_code("ef8d9a0b717d3cb0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jiwanhur/unlockmgm 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_parameter_device Ran
ran; our contract draft was wrong, not the code
jiwanhur/unlockmgm/muse/modeling_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from leaplabthu/enat, is pointer only (licence: NONE) · get_code("bfdddec04a7257ca")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jiwanhur/unlockmgm 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_parameter_dtype Ran
ran; our contract draft was wrong, not the code
jiwanhur/unlockmgm/muse/modeling_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from leaplabthu/enat, is pointer only (licence: NONE) · get_code("4f52e71d06a15422")
How it ran

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

load_state_dict Ran
ran; our contract draft was wrong, not the code
jiwanhur/unlockmgm/muse/modeling_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from leaplabthu/enat, is pointer only (licence: NONE) · get_code("934f2eb98d647821")
How it ran

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

make_attention_mask Ran
ran; our contract draft was wrong, not the code
huggingface/open-muse/muse/modeling_transformer.py
code served (permissive licence) · get_code("b22b48bb429101bb")
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 Tensor, ndim 4, dtype family float, shape (2, 1, 3, 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 torch.nn.functional as F

torch.manual_seed(0)

# Create small tensors for query_input and key_input
# query_input shape: (batch=2, query_len=3)
query_input = torch.tensor([
    [1.0, 0.0, 1.0],
    [0.0, 1.0, 0.0]
], dtype=torch.float32)

# key_input shape: (batch=2, key_len=4)
key_input = torch.tensor([
    [1.0, 1.0, 0.0, 1.0],
    [0.0, 1.0, 1.0, 0.0]
], dtype=torch.float32)

# Define a simple pairwise function
def pairwise_fn(x, y):
    return torch.mul(x, y)

ARGS = {
    "query_input": query_input,
    "key_input": key_input,
    "pairwise_fn": pairwise_fn
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
einops, numpy, torch, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 1, 3, 4) — shape (2, 1, 3, 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
make_attention_mask Ran
ran; our contract draft was wrong, not the code
jiwanhur/unlockmgm/muse/modeling_transformer.py
pointer only (licence: NONE) · get_code("e88526ab8fc3ebc4")
How it ran

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

prob_mask_like Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
huggingface/open-muse/muse/modeling_transformer.py
code served (permissive licence) · get_code("1a6c10e37cb97711")
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 Tensor, ndim 3, dtype family float, shape (2, 4, 3) 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 math
from functools import partial
from typing import Callable, Optional
import numpy as np
import torch.nn.functional as F
from einops import rearrange
from torch import nn
from torch.utils.checkpoint import checkpoint
from tqdm import tqdm

def uniform(shape, min=0, max=1, device=None):
    return torch.zeros(shape, device=device).float().uniform_(0, 1)

def prob_mask_like(shape, prob, device=None):
    if prob == 1:
        return torch.ones(shape, device=device, dtype=torch.bool)
    elif prob == 0:
        return torch.zeros(shape, device=device, dtype=torch.bool)
    else:
        return uniform(shape, device=device) < prob

torch.manual_seed(0)

ARGS = {
    "shape": (2, 4, 3),
    "prob": 0.5,
    "device": None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
einops, numpy, torch, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (2, 4, 3) — shape (2, 4, 3) 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
prob_mask_like Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jiwanhur/unlockmgm/muse/modeling_transformer.py
pointer only (licence: NONE) · get_code("162f6eae613812c6")
How it ran

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

soft_target_cross_entropy Ran
ran; our contract draft was wrong, not the code
huggingface/open-muse/training/train_maskgit_imagenet.py
code served (permissive licence) · get_code("d8437c41cc2a860f")
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 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.functional as F

torch.manual_seed(0)

# Create logits tensor: shape (batch=2, seq_len=5, vocab=4)
# After slicing [:, 1:], becomes (2, 4, 4)
logits = torch.randn(2, 5, 4)

# Create targets tensor: shape (batch=2, seq_len=5)
# After slicing [:, 1:], becomes (2, 4)
# Values should be -100 (padding) or valid indices
targets = torch.tensor([
    [-100, 0, 1, 2, -100],
    [1, 2, 0, -100, -100]
])

# Create soft_targets tensor: shape (batch=2, seq_len=4, num_classes=3)
# This should match the shape after logits slicing and truncation
soft_targets = torch.softmax(torch.randn(2, 4, 3), dim=-1)

ARGS = {
    "logits": logits,
    "targets": targets,
    "soft_targets": soft_targets
}
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 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
uniform Ran
ran; our contract draft was wrong, not the code
huggingface/open-muse/muse/modeling_transformer.py
code served (permissive licence) · get_code("7daf2f4e6899de97")
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 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)

ARGS = {
    "shape": (2, 4),
    "min": 0,
    "max": 1,
    "device": None,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
einops, numpy, torch, tqdm — 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
uniform Ran
ran; our contract draft was wrong, not the code
jiwanhur/unlockmgm/muse/modeling_transformer.py
pointer only (licence: NONE) · get_code("66e51521e0875290")
How it ran

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

Normalize Not yet run
unverified (harvested, no recorded run)
jiwanhur/unlockmgm/muse/modeling_movq.py
pointer only (licence: NONE) · get_code("4c71b9128b894511")
How it ran

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

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 8 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 6 the same month, 5 later) and 1 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_parameter_device 10 other papers
8 dated earlier, 1 the same month, 1 later
2304.05568 (2023-04)
Improving Diffusion Models for Scene Text Editing with Dual Encoders
2306.05720 (2023-06)
Beyond Surface Statistics: Scene Representations in a Latent Diffusion Model
2307.10829 (2023-07)
Exact Diffusion Inversion via Bi-directional Integration Approximation
and 7 more not named here
get_parameter_dtype 10 other papers
8 dated earlier, 1 the same month, 1 later
2304.05568 (2023-04)
Improving Diffusion Models for Scene Text Editing with Dual Encoders
2306.05720 (2023-06)
Beyond Surface Statistics: Scene Representations in a Latent Diffusion Model
2307.10829 (2023-07)
Exact Diffusion Inversion via Bi-directional Integration Approximation
and 7 more not named here
flatten_omega_conf 3 other papers
1 dated earlier, 1 the same month, 1 later
2301.00704 (2023-01)
Muse: Text-To-Image Generation via Masked Generative Transformers
2410.06264 (2024-10)
Think While You Generate: Discrete Diffusion with Planned Denoising
2505.23380 (2025-05)
UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning
load_state_dict 2 other papers
1 dated earlier, 1 later
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
make_attention_mask 2 other papers
1 dated earlier, 1 the same month
2301.00704 (2023-01)
Muse: Text-To-Image Generation via Masked Generative Transformers
2410.20366 (2024-10)
Rethinking Reconstruction-based Graph-Level Anomaly Detection: Limitations and a Simple Remedy
prob_mask_like 2 other papers
1 dated earlier, 1 the same month
2301.00704 (2023-01)
Muse: Text-To-Image Generation via Masked Generative Transformers
2410.20366 (2024-10)
Rethinking Reconstruction-based Graph-Level Anomaly Detection: Limitations and a Simple Remedy
soft_target_cross_entropy 2 other papers
1 dated earlier, 1 later
2301.00704 (2023-01)
Muse: Text-To-Image Generation via Masked Generative Transformers
2505.23380 (2025-05)
UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning
uniform 2 other papers
1 dated earlier, 1 the same month
2301.00704 (2023-01)
Muse: Text-To-Image Generation via Masked Generative Transformers
2410.20366 (2024-10)
Rethinking Reconstruction-based Graph-Level Anomaly Detection: Limitations and a Simple Remedy

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

Comparison of sampled images using 18-step MaskGIT [4] without (top) and with the proposed self-guidance (bottom) on ImageNet 512×512 (left) and 256×256 (right) resolutions. Each paired image is sampled using the same random seed and sampling hyperparameters. The proposed self-guidance effectively improves the capabilities of the masked generative models.

For agents

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

get_harvested_code_for_paper("2410.13136")
get_code_for_paper("2410.13136")
have("2410.13136")

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

curl https://syntology.ai/api/ran/2410.13136.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.13136.svg)](https://syntology.ai/paper/2410.13136)

Connect an agent — have() is free.