SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.19009 · ICML · 2024

Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decoding

Julian Mcauley, Yuan Gao, Eric Xing, Zhiting Hu, Yu Wang, Shuguang Cui, Zhen Li, Guangyi Liu, Zeyu Feng, Qiyu Wu, Liping Tang, Zichao Yang

arXiv · PDF · Open in the Atlas

Code that ran

22 of 24 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (13 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 1 violated it and 13 have no contract verdict; 8 failures of our instrument; 2 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/2402.19009.json · badge: /api/ran/2402.19009.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
guangyliu/eddpm canonical (classifier label)
classifier basis: classifier_2025
17 ran · 1 no recorded run
guangyliu/EDDPM canonical (classifier label)
classifier basis: census
5 ran · 1 no recorded run
FunctionStatusWhere it lives
BaseBottleneck Ran
ran on a synthesized input · constructed an object; no result was computed
guangyliu/eddpm/Protein/codes/nn/models.py
pointer only (licence: NONE) · get_code("b38e2abd4e8693ef")
How it ran

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

BaseModel Ran
ran on a synthesized input · constructed an object; no result was computed
guangyliu/eddpm/Protein/codes/nn/models.py
pointer only (licence: NONE) · get_code("74b42ac1a61a294c")
How it ran

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

BaseRegressor Ran
ran on a synthesized input · constructed an object; no result was computed
guangyliu/eddpm/Protein/codes/nn/models.py
pointer only (licence: NONE) · get_code("06050df9b6e9539c")
How it ran

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

Block Ran
ran on a synthesized input · constructed an object; no result was computed
guangyliu/eddpm/Protein/codes/nn/models.py
pointer only (licence: NONE) · get_code("d6f0bd13ce861a0c")
How it ran

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

DDPM Ran
ran on a synthesized input · constructed an object; no result was computed
guangyliu/eddpm/Protein/codes/nn/models.py
pointer only (licence: NONE) · get_code("f376daeaa8e94192")
How it ran

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

DropoutRegressor Ran
ran on a synthesized input · constructed an object; no result was computed
guangyliu/eddpm/Protein/codes/nn/models.py
pointer only (licence: NONE) · get_code("897d4be7d966b05b")
How it ran

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

EncoderBlock Ran
ran on a synthesized input · constructed an object; no result was computed
guangyliu/eddpm/Protein/codes/nn/models.py
pointer only (licence: NONE) · get_code("73cd3359ae45d6c1")
How it ran

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

MLPLNAct Ran
ran on a synthesized input · constructed an object; no result was computed
guangyliu/eddpm/Protein/codes/nn/models.py
pointer only (licence: NONE) · get_code("971501d576e063ff")
How it ran

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

MLPSkipNet Ran
ran on a synthesized input · constructed an object; no result was computed
guangyliu/eddpm/Protein/codes/nn/models.py
pointer only (licence: NONE) · get_code("83b87fdcd50ae47f")
How it ran

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

MultiheadAttention Ran
ran on a synthesized input · constructed an object; no result was computed
guangyliu/eddpm/Protein/codes/nn/models.py
pointer only (licence: NONE) · get_code("ebbb4cab1eb5afaf")
How it ran

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

PositionalEncoding Ran
ran on a synthesized input · constructed an object; no result was computed
guangyliu/eddpm/Protein/codes/nn/models.py
pointer only (licence: NONE) · get_code("ea11dcdf0fc3269a")
How it ran

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

SpectralRegressor Ran
ran on a synthesized input · constructed an object; no result was computed
guangyliu/eddpm/Protein/codes/nn/models.py
pointer only (licence: NONE) · get_code("07eb713c3f7475b0")
How it ran

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

TransformerEncoder Ran
ran on a synthesized input · constructed an object; no result was computed
guangyliu/eddpm/Protein/codes/nn/models.py
pointer only (licence: NONE) · get_code("8a9cafe52195db96")
How it ran

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

ddpm_schedules Ran
ran; our contract draft was wrong, not the code
guangyliu/eddpm/Protein/codes/nn/models.py
pointer only (licence: NONE) · get_code("30750d439887db4d")
How it ran

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

jsonable Ran
ran, violated the contract we drafted
guangyliu/EDDPM/Image/config_base.py
pointer only (licence: NONE) · get_code("3436fefeb3a4b49a")
How it ran

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

resize_and_convert Ran
ran; our contract draft was wrong, not the code
guangyliu/EDDPM/Image/data_resize_bedroom.py
code served (permissive licence) · get_code("f36fb3b9b1239da0")
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 bytes. 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.

from io import BytesIO
from PIL import Image
import torch

torch.manual_seed(0)

# Create a small PIL Image object
# The function expects a PIL Image since it calls .save() on it
img = Image.new('RGB', (100, 100), color='red')

# size parameter: tuple of (height, width) for resize
size = (64, 64)

# resample parameter: PIL resampling filter
# Common choices are Image.BILINEAR, Image.NEAREST, etc.
resample = Image.BILINEAR

# quality parameter: JPEG/WebP quality (default 100)
quality = 95

ARGS = {
    'img': img,
    'size': size,
    'resample': resample,
    'quality': quality
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bytes — a bytes output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a bytes 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
resize_multiple Ran
ran; our contract draft was wrong, not the code
guangyliu/EDDPM/Image/data_resize_bedroom.py
code served (permissive licence) · get_code("b6e307e73df01911")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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.

from PIL import Image
import torch

# Create a small test image
img = Image.new('RGB', (256, 256), color='red')

# Define ARGS dictionary with all parameters for resize_multiple
ARGS = {
    'img': img,
    'sizes': (128, 256, 512),
    'resample': Image.LANCZOS,
    'quality': 85
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
resize_worker Ran
ran; our contract draft was wrong, not the code
guangyliu/EDDPM/Image/data_resize_bedroom.py
code served (permissive licence) · get_code("a046145c828624ad")
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 tuple. 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.

from PIL import Image
import torch

torch.manual_seed(0)

# Create a small RGB image for testing
img = Image.new('RGBA', (256, 256), color=(255, 0, 0, 255))

# Define the arguments dictionary for resize_worker
ARGS = {
    'idx': 0,
    'img': img,
    'sizes': (128, 256, 512),
    'resample': Image.LANCZOS
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
scaled_dot_product Ran
ran; our contract draft was wrong, not the code
guangyliu/eddpm/Protein/codes/nn/models.py
pointer only (licence: NONE) · get_code("9e67eeb355787261")
How it ran

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

str2auxnetwork Ran
ran; our contract draft was wrong, not the code
guangyliu/eddpm/Protein/codes/nn/models.py
pointer only (licence: NONE) · get_code("af78970db657f767")
How it ran

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

timestep_embedding Ran
ran; our contract draft was wrong, not the code
guangyliu/eddpm/Protein/codes/nn/models.py
pointer only (licence: NONE) · get_code("df97c543ba6aa8c1")
How it ran

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

unpack_bz2 Ran
ran; our contract draft was wrong, not the code
guangyliu/EDDPM/Image/align.py
code served (permissive licence) · get_code("8b346c500755d6bc")
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 bz2
import os
import tempfile

# Create a temporary directory for testing
temp_dir = tempfile.mkdtemp()

# Create a test bz2 file
test_content = b"This is test data for unpacking"
src_path = os.path.join(temp_dir, "test_file.bz2")
with bz2.BZ2File(src_path, 'wb') as f:
    f.write(test_content)

ARGS = {
    'src_path': src_path
}
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
RelsoDiffusion Not yet run
unverified (harvested, no recorded run)
guangyliu/eddpm/Protein/codes/nn/models.py
pointer only (licence: NONE) · get_code("35f5c7853a3a411e")
How it ran

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

get_file Not yet run
unverified (harvested, no recorded run)
guangyliu/EDDPM/Image/align.py
code served (permissive licence) · get_code("f93f74df8c200466")
How it ran

no invocation recorded.

Also present in other papers' code

Of 24 samples lifted from this paper's linked repositories, 24 carry a function identity and 0 do not. Of the 24 distinct functions with an identity, 9 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 0 the same month, 2 later) and 15 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
jsonable 5 other papers
4 dated earlier, 1 later
2111.15640 (2021-11)
Diffusion Autoencoders: Toward a Meaningful and Decodable Representation
2211.12500 (2022-11)
Person Image Synthesis via Denoising Diffusion Model
2308.01316 (2023-08)
Patched Denoising Diffusion Models For High-Resolution Image Synthesis
and 2 more not named here
resize_multiple 5 other papers
5 dated earlier
2111.15640 (2021-11)
Diffusion Autoencoders: Toward a Meaningful and Decodable Representation
2203.14954 (2022-03)
GIRAFFE HD: A High-Resolution 3D-aware Generative Model
2210.16559 (2022-10)
Few-shot Image Generation via Adaptation-Aware Kernel Modulation
and 2 more not named here
get_file 2 other papers
2 dated earlier
2111.15640 (2021-11)
Diffusion Autoencoders: Toward a Meaningful and Decodable Representation
2308.09223 (2023-08)
DMCVR: Morphology-Guided Diffusion Model for 3D Cardiac Volume Reconstruction
scaled_dot_product
brick of this paper's assembly: helper
2 other papers
1 dated earlier, 1 later
2201.09948 (2022-01)
ReLSO: A Transformer-based Model for Latent Space Optimization and Generation of Proteins
2410.16432 (2024-10)
Fair Bilevel Neural Network (FairBiNN): On Balancing fairness and accuracy via Stackelberg Equilibrium
unpack_bz2 2 other papers
2 dated earlier
2111.15640 (2021-11)
Diffusion Autoencoders: Toward a Meaningful and Decodable Representation
2308.09223 (2023-08)
DMCVR: Morphology-Guided Diffusion Model for 3D Cardiac Volume Reconstruction
TransformerEncoder
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2305.00664 (2023-05)
EvoluNet: Advancing Dynamic Non-IID Transfer Learning on Graphs
resize_and_convert 1 other paper
1 dated earlier
2111.15640 (2021-11)
Diffusion Autoencoders: Toward a Meaningful and Decodable Representation
resize_worker 1 other paper
1 dated earlier
2111.15640 (2021-11)
Diffusion Autoencoders: Toward a Meaningful and Decodable Representation
str2auxnetwork
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2201.09948 (2022-01)
ReLSO: A Transformer-based Model for Latent Space Optimization and Generation of Proteins

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

The vast applications of deep generative models are anchored in three core capabilitiesgenerating new instances, reconstructing inputs, and learning compact representations-across various data types, such as discrete text/protein sequences and continuous images. Existing model families, like variational autoencoders (VAEs), generative adversarial networks (GANs), autoregressive models, and (latent) diffusion models, generally excel in specific capabilities and data types but fall short in others. We introduce Generalized Encoding-Decoding Diffusion Probabilistic Models (EDDPMs) which integrate the core capabilities for broad applicability and enhanced performance. EDDPMs generalize the Gaussian noising-denoising in standard diffusion by introducing parameterized encoding-decoding. Crucially, EDDPMs are compatible with the wellestablished diffusion model objective and training recipes, allowing effective learning of the encoder-decoder parameters jointly with diffusion. By choosing appropriate encoder/decoder (e.g., large language models), EDDPMs naturally apply to different data types. Extensive experiments on text, proteins, and images demonstrate the flexibility to handle diverse data and tasks and the strong improvement over various existing models. Code is available at https: //github.com/guangyliu/EDDPM

For agents

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

get_harvested_code_for_paper("2402.19009")
get_code_for_paper("2402.19009")
have("2402.19009")

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

curl https://syntology.ai/api/ran/2402.19009.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.19009.svg)](https://syntology.ai/paper/2402.19009)

Connect an agent — have() is free.