SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.06389 · 2023

Learning Stackable and Skippable LEGO Bricks for Efficient, Reconfigurable, and Variable-Resolution Diffusion Modeling

arXiv · PDF · Open in the Atlas

Code that ran

13 of 17 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; 4 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 9 failures of our instrument; 4 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/2310.06389.json · badge: /api/ran/2310.06389.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
JegZheng/LEGODiffusion canonical (classifier label)
classifier basis: census
13 ran · 4 no recorded run
FunctionStatusWhere it lives
constant Ran
ran; our contract draft was wrong, not the code
JegZheng/LEGODiffusion/torch_utils/misc.py
pointer only (licence: MIT); the stored copy get_code serves, from xfetus/fetal-ultrasound-edm2, is pointer only (licence: NONE) · get_code("6d32f9cf6f29b386")
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 xfetus/fetal-ultrasound-edm2, 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.

file_ext Ran
ran; our contract draft was wrong, not the code
JegZheng/LEGODiffusion/dataset_tool.py
pointer only (licence: MIT); the stored copy get_code serves, from pdillis/stylegan3-fun, is pointer only (licence: NOASSERTION) · get_code("a2b45afa097b55b6")
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 pdillis/stylegan3-fun, 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.

find_latest_checkpoint Ran
ran; our contract draft was wrong, not the code
JegZheng/LEGODiffusion/generate.py
code served (permissive licence) · get_code("54145599584b3b04")
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 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 os
import tempfile
import shutil

# Create a temporary directory structure with checkpoint files
temp_dir = tempfile.mkdtemp()

# Create subdirectories
subdir1 = os.path.join(temp_dir, 'checkpoints')
subdir2 = os.path.join(temp_dir, 'checkpoints', 'nested')
os.makedirs(subdir1)
os.makedirs(subdir2)

# Create checkpoint files with various numbers
checkpoint_files = [
    os.path.join(subdir1, 'network-snapshot-100.pkl'),
    os.path.join(subdir1, 'network-snapshot-50.pkl'),
    os.path.join(subdir2, 'network-snapshot-200.pkl'),
    os.path.join(subdir2, 'network-snapshot-150.pkl'),
    os.path.join(temp_dir, 'network-snapshot-75.pkl'),
]

# Create the files
for filepath in checkpoint_files:
    with open(filepath, 'w') as f:
        f.write('dummy checkpoint')

# Also create some non-checkpoint files that should be ignored
with open(os.path.join(subdir1, 'network-snapshot-invalid.pkl'), 'w') as f:
    f.write('dummy')
with open(os.path.join(subdir1, 'other-file-100.pkl'), 'w') as f:
    f.write('dummy')

ARGS = {
    'directory': temp_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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
format_time Ran
ran; our contract draft was wrong, not the code
JegZheng/LEGODiffusion/dnnlib/util.py
code served (permissive licence) · get_code("674eca7b9e1b6439")
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 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 numpy as np
from typing import Union

# Test with various time values
ARGS = {
    "seconds": 3661.7  # 1 hour, 1 minute, 1.7 seconds - tests rounding and all format branches
}
Setup block drafted by
a language model, Claude Haiku 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 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
format_time_brief Ran
ran; our contract draft was wrong, not the code
JegZheng/LEGODiffusion/dnnlib/util.py
code served (permissive licence) · get_code("32af001972a0699f")
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 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 numpy as np
from typing import Union

# Test with various time values
ARGS = {
    "seconds": 45.7  # A float value that will be rounded to 46 seconds
}
Setup block drafted by
a language model, Claude Haiku 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 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
get_2d_sincos_pos_embed Ran
ran, honoured the contract we drafted
JegZheng/LEGODiffusion/training/lego_models.py
code served (permissive licence) · get_code("c92c27c924b517e8")
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 ndarray, ndim 2, dtype family float, shape (18, 8) 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 numpy as np

# Define ARGS dict with all parameters for get_2d_sincos_pos_embed
ARGS = {
    "embed_dim": 8,
    "grid_size": 4,
    "cls_token": True,
    "extra_tokens": 2,
}
Setup block drafted by
a language model, Claude Haiku 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 ndarray, ndim 2, dtype family float, shape (18, 8) — shape (18, 8) 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
maybe_min Ran
ran, honoured the contract we drafted
JegZheng/LEGODiffusion/dataset_tool.py
pointer only (licence: MIT); the stored copy get_code serves, from pdillis/stylegan3-fun, is pointer only (licence: NOASSERTION) · get_code("dd1dc700e87f36cc")
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 pdillis/stylegan3-fun, 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.

modulate Ran
ran; our contract draft was wrong, not the code
JegZheng/LEGODiffusion/training/lego_models.py
code served (permissive licence) · get_code("03310bba324ae4fb")
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

torch.manual_seed(0)

# Create small tensors for the modulate function
# x: input tensor with shape (batch_size, feature_dim)
x = torch.randn(2, 4)

# shift: tensor that will be unsqueezed to (batch_size, 1)
# so it should have shape (batch_size,)
shift = torch.randn(2)

# scale: tensor that will be unsqueezed to (batch_size, 1)
# so it should have shape (batch_size,)
scale = torch.randn(2)

ARGS = {
    "x": x,
    "shift": shift,
    "scale": scale,
}
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
params_and_buffers Ran
ran; our contract draft was wrong, not the code
JegZheng/LEGODiffusion/torch_utils/misc.py
pointer only (licence: MIT); the stored copy get_code serves, from AMAP-ML/DCW, is pointer only (licence: NOASSERTION) · get_code("b5ae713738eb4d27")
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 AMAP-ML/DCW, 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.

parse_int_list Ran
ran, honoured the contract we drafted
JegZheng/LEGODiffusion/generate.py
pointer only (licence: MIT); the stored copy get_code serves, from newbeeer/stf, is pointer only (licence: NONE) · get_code("cacd4f6ec202d9b4")
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 newbeeer/stf, 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.

parse_tuple Ran
ran, honoured the contract we drafted
JegZheng/LEGODiffusion/dataset_tool.py
pointer only (licence: MIT); the stored copy get_code serves, from xfetus/fetal-ultrasound-edm2, is pointer only (licence: NONE) · get_code("07b21b35ecb4815c")
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 xfetus/fetal-ultrasound-edm2, 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.

profiled_function Ran
ran; our contract draft was wrong, not the code
JegZheng/LEGODiffusion/torch_utils/misc.py
pointer only (licence: MIT); the stored copy get_code serves, from AMAP-ML/DCW, is pointer only (licence: NOASSERTION) · get_code("f4664bbb3c2df6e0")
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 AMAP-ML/DCW, 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.

weight_init Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
JegZheng/LEGODiffusion/training/networks.py
code served (permissive licence) · get_code("d41a4250066bce93")
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 Tensor, ndim 2, dtype family float, shape (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 numpy as np

torch.manual_seed(0)

ARGS = {
    'shape': (4, 3),
    'mode': 'xavier_uniform',
    'fan_in': 10,
    'fan_out': 8,
}
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 Tensor, ndim 2, dtype family float, shape (4, 3) — shape (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
ask_yes_no Not yet run
unverified (harvested, no recorded run)
JegZheng/LEGODiffusion/dnnlib/util.py
code served (permissive licence) · get_code("9d31d2c4cd16bb2d")
How it ran

no invocation recorded.

edm_lego_sampler Not yet run
unverified (harvested, no recorded run)
JegZheng/LEGODiffusion/generate.py
code served (permissive licence) · get_code("38a46049a4af72ae")
How it ran

no invocation recorded.

get_2d_sincos_pos_embed_from_grid Not yet run
unverified (harvested, no recorded run)
JegZheng/LEGODiffusion/training/lego_models.py
code served (permissive licence) · get_code("665d8a4e8f673a4c")
How it ran

no invocation recorded.

is_persistent Not yet run
unverified (harvested, no recorded run)
JegZheng/LEGODiffusion/torch_utils/persistence.py
pointer only (licence: MIT); the stored copy get_code serves, from AMAP-ML/DCW, is pointer only (licence: NOASSERTION) · get_code("e8b31ffccfa05efc")
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 AMAP-ML/DCW, 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. No invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 15 are also present in other papers whose code we hold (15 with at least one paper dated earlier, 15 the same month, 15 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

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

FunctionAlso present inEarliest-datedOthers named
get_2d_sincos_pos_embed_from_grid 190 other papers
47 dated earlier, 5 the same month, 137 later, 1 same year, order not determinable · 65 only as an assembly brick
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
2105.12723 (2021-05)
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding
2111.06377 (2021-11)
Masked Autoencoders Are Scalable Vision Learners
and 187 more not named here
modulate 101 other papers
7 dated earlier, 2 the same month, 91 later, 1 undated · 29 only as an assembly brick
2202.04200 (2022-02)
MaskGIT: Masked Generative Image Transformer
2203.10897 (2022-03)
Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression
2212.09748 (2022-12)
Scalable Diffusion Models with Transformers
and 98 more not named here
format_time 73 other papers
14 dated earlier, 5 the same month, 53 later, 1 undated
2004.00049 (2020-04)
In-Domain GAN Inversion for Real Image Editing
2004.11660 (2020-04)
Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning
2108.00946 (2021-08)
StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators
and 70 more not named here
ask_yes_no 69 other papers
14 dated earlier, 5 the same month, 49 later, 1 undated
2004.00049 (2020-04)
In-Domain GAN Inversion for Real Image Editing
2004.11660 (2020-04)
Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning
2108.00946 (2021-08)
StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators
and 66 more not named here
get_2d_sincos_pos_embed 69 other papers
5 dated earlier, 1 the same month, 63 later · 12 only as an assembly brick
2203.10897 (2022-03)
Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression
2212.09748 (2022-12)
Scalable Diffusion Models with Transformers
2303.14389 (2023-03)
Masked Diffusion Transformer is a Strong Image Synthesizer
and 66 more not named here
format_time_brief 68 other papers
12 dated earlier, 4 the same month, 51 later, 1 undated
2108.00946 (2021-08)
StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators
2202.00273 (2022-02)
StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets
2206.07695 (2022-06)
VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids
and 65 more not named here
weight_init 49 other papers
8 dated earlier, 4 the same month, 37 later · 1 only as an assembly brick
2303.10137 (2023-03)
A Recipe for Watermarking Diffusion Models
2305.15266 (2023-05)
Diffusion-Based Audio Inpainting
2305.16269 (2023-05)
UDPM: Upsampling Diffusion Probabilistic Models
and 46 more not named here
parse_int_list 37 other papers
10 dated earlier, 2 the same month, 25 later
2206.00364 (2022-06)
Elucidating the Design Space of Diffusion-Based Generative Models
2302.00670 (2023-02)
Stable Target Field for Reduced Variance Score Estimation in Diffusion Models
2302.04265 (2023-02)
PFGM++: Unlocking the Potential of Physics-Inspired Generative Models
and 34 more not named here
file_ext 35 other papers
13 dated earlier, 2 the same month, 20 later
2106.07023 (2021-06)
Styleformer: Transformer based Generative Adversarial Networks with Style Vector
2111.02175 (2021-11)
Discriminator Synthesis: On reusing the other half of Generative Adversarial Networks
2111.13792 (2021-11)
LAFITE: Towards Language-Free Training for Text-to-Image Generation
and 32 more not named here
maybe_min 35 other papers
13 dated earlier, 2 the same month, 20 later
2106.07023 (2021-06)
Styleformer: Transformer based Generative Adversarial Networks with Style Vector
2111.02175 (2021-11)
Discriminator Synthesis: On reusing the other half of Generative Adversarial Networks
2111.13792 (2021-11)
LAFITE: Towards Language-Free Training for Text-to-Image Generation
and 32 more not named here
constant 26 other papers
4 dated earlier, 1 the same month, 21 later
2306.06991 (2023-06)
Fast Diffusion Model
2308.15321 (2023-08)
Elucidating the Exposure Bias in Diffusion Models
2309.03350 (2023-09)
Relay Diffusion: Unifying diffusion process across resolutions for image synthesis
and 23 more not named here
is_persistent 20 other papers
4 dated earlier, 1 the same month, 15 later
2306.06991 (2023-06)
Fast Diffusion Model
2308.15321 (2023-08)
Elucidating the Exposure Bias in Diffusion Models
2309.03350 (2023-09)
Relay Diffusion: Unifying diffusion process across resolutions for image synthesis
and 17 more not named here
parse_tuple 20 other papers
5 dated earlier, 2 the same month, 13 later
2303.10137 (2023-03)
A Recipe for Watermarking Diffusion Models
2306.06991 (2023-06)
Fast Diffusion Model
2308.15321 (2023-08)
Elucidating the Exposure Bias in Diffusion Models
and 17 more not named here
params_and_buffers 18 other papers
4 dated earlier, 1 the same month, 13 later
2306.06991 (2023-06)
Fast Diffusion Model
2308.15321 (2023-08)
Elucidating the Exposure Bias in Diffusion Models
2309.03350 (2023-09)
Relay Diffusion: Unifying diffusion process across resolutions for image synthesis
and 15 more not named here
profiled_function 18 other papers
4 dated earlier, 1 the same month, 13 later
2306.06991 (2023-06)
Fast Diffusion Model
2308.15321 (2023-08)
Elucidating the Exposure Bias in Diffusion Models
2309.03350 (2023-09)
Relay Diffusion: Unifying diffusion process across resolutions for image synthesis
and 15 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

Diffusion models excel at generating photo-realistic images but come with significant computational costs in both training and sampling. While various techniques address these computational challenges, a less-explored issue is designing an efficient and adaptable network backbone for iterative refinement. Current options like U-Net and Vision Transformer often rely on resource-intensive deep networks and lack the flexibility needed for generating images at variable resolutions or with a smaller network than used in training. This study introduces LEGO bricks, which seamlessly integrate Local-feature Enrichment and Global-content Orchestration. These bricks can be stacked to create a test-time reconfigurable diffusion backbone, allowing selective skipping of bricks to reduce sampling costs and generate higher-resolution images than the training data. LEGO bricks enrich local regions with an MLP and transform them using a Transformer block while maintaining a consistent full-resolution image across all bricks. Experimental results demonstrate that LEGO bricks enhance training efficiency, expedite convergence, and facilitate variable-resolution image generation while maintaining strong generative performance. Moreover, LEGO significantly reduces sampling time compared to other methods, establishing it as a valuable enhancement for diffusion models. Our code and project page are available at https://jegzheng.github.io/LEGODiffusion.

For agents

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

get_harvested_code_for_paper("2310.06389")
get_code_for_paper("2310.06389")
have("2310.06389")

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

curl https://syntology.ai/api/ran/2310.06389.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.06389.svg)](https://syntology.ai/paper/2310.06389)

Connect an agent — have() is free.