SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.01140 · ICML · 2023

Geometric Latent Diffusion Models for 3D Molecule Generation

Stefano Ermon, Jure Leskovec, Minkai Xu, Ron Dror, Alexander Powers

arXiv · PDF · Open in the Atlas

Code that ran

5 of 9 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 1 has no contract verdict; 4 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/2305.01140.json · badge: /api/ran/2305.01140.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
minkaixu/geoldm canonical (classifier label)
classifier basis: census
3 ran · 3 no recorded run
rlacombe/accgeoldm community (classifier label)
classifier basis: plan_row
2 ran · 1 no recorded run
FunctionStatusWhere it lives
compute_loss_and_nll Ran
ran; our contract draft was wrong, not the code
rlacombe/accgeoldm/qm9/losses.py
code served (permissive licence) · get_code("4ed06d5114046b7e")
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.

import torch
import torch.nn as nn
from torch.distributions import Poisson

torch.manual_seed(0)

# Create a minimal args object
class Args:
    def __init__(self):
        self.probabilistic_model = 'diffusion'

args = Args()

# Create a minimal generative model that accepts the expected inputs
class GenerativeModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 1)
    
    def forward(self, x, h, node_mask, edge_mask, context):
        # x: (bs, n_nodes, n_dims)
        # Returns nll of shape (bs,)
        bs = x.size(0)
        return torch.randn(bs)

generative_model = GenerativeModel()

# Create nodes_dist with log_prob method
class NodesDist:
    def log_prob(self, N):
        # N is a long tensor of shape (bs,)
        return torch.randn(N.size(0))

nodes_dist = NodesDist()

# Create tensors with distinct sizes
bs = 2
n_nodes = 3
n_dims = 4

x = torch.randn(bs, n_nodes, n_dims)
h = torch.randn(bs, n_nodes, 5)
node_mask = torch.ones(bs, n_nodes, 1)
edge_mask = torch.ones(bs, n_nodes, n_nodes)
context = torch.randn(bs, 6)

ARGS = {
    'args': args,
    'generative_model': generative_model,
    'nodes_dist': nodes_dist,
    'x': x,
    'h': h,
    'node_mask': node_mask,
    'edge_mask': edge_mask,
    'context': context
}
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 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
gradient_clipping Ran
ran on a synthesized input
minkaixu/geoldm/utils.py
code served (permissive licence) · get_code("e033860884ced8ac")
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 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)

# Create a simple flow model with parameters
class SimpleFlow(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        return self.linear2(torch.relu(self.linear1(x)))

# Instantiate the flow model
flow = SimpleFlow()

# Create some dummy input and output to enable gradient computation
x = torch.randn(2, 4)
y = torch.randn(2, 2)

# Forward pass and loss computation to generate gradients
output = flow(x)
loss = torch.nn.functional.mse_loss(output, y)
loss.backward()

# Create a simple queue-like object to track gradient norms
class GradNormQueue:
    def __init__(self):
        self.values = [0.5, 0.7, 0.6, 0.8]
    
    def mean(self):
        return torch.tensor(sum(self.values) / len(self.values))
    
    def std(self):
        mean_val = sum(self.values) / len(self.values)
        variance = sum((x - mean_val) ** 2 for x in self.values) / len(self.values)
        return torch.tensor(variance ** 0.5)
    
    def add(self, value):
        self.values.append(value)

gradnorm_queue = GradNormQueue()

ARGS = {
    "flow": flow,
    "gradnorm_queue": gradnorm_queue,
}
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 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
random_rotation Ran
ran; our contract draft was wrong, not the code
minkaixu/geoldm/utils.py
code served (permissive licence) · get_code("e372872a463628a7")
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 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 numpy as np

torch.manual_seed(0)

# Test case 1: 2D rotation
# x should have shape (batch_size, n_nodes, n_dims)
# For 2D case: (bs, n_nodes, 2)
x_2d = torch.randn(2, 4, 2)

# Test case 2: 3D rotation
# For 3D case: (bs, n_nodes, 3)
x_3d = torch.randn(2, 4, 3)

# The function takes one parameter: x
# We'll test with the 3D case as it exercises more code
ARGS = {
    "x": x_3d
}
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 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
sum_except_batch Ran
ran; our contract draft was wrong, not the code
rlacombe/accgeoldm/qm9/losses.py
code served (permissive licence) · get_code("90c529ca8e85d3db")
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 1, dtype family float, shape (2,) 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)

# The function takes a tensor x, reshapes it to (batch_size, -1),
# and sums across the flattened dimension. We need a multi-dimensional tensor.
x = torch.randn(2, 4, 3)  # batch=2, other dims flattened to 12

ARGS = {
    "x": x
}
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 Tensor, ndim 1, dtype family float, shape (2,) — shape (2,) 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
unsorted_segment_sum Ran
ran; our contract draft was wrong, not the code
minkaixu/geoldm/egnn/egnn.py
code served (permissive licence) · get_code("dfdf6dc1a0720e57")
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 (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 numpy as np

torch.manual_seed(0)

# Create tiny tensors for testing
# data: shape (batch_size, feature_dim) - the values to sum
# segment_ids: shape (batch_size,) - which segment each row belongs to
# num_segments: int - total number of segments

batch_size = 2
feature_dim = 4
num_segments = 3

data = torch.randn(batch_size, feature_dim)
segment_ids = torch.tensor([0, 2], dtype=torch.long)

ARGS = {
    "data": data,
    "segment_ids": segment_ids,
    "num_segments": num_segments,
}
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 (3, 4) — shape (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
get_args_gen Not yet run
unverified (harvested, no recorded run)
rlacombe/accgeoldm/eval_conditional_qm9.py
code served (permissive licence) · get_code("f576c0a0e0ae29c2")
How it ran

no invocation recorded.

get_dataset_info Not yet run
unverified (harvested, no recorded run)
minkaixu/geoldm/configs/datasets_config.py
code served (permissive licence) · get_code("6ee9e481f2c35447")
How it ran

no invocation recorded.

load_model Not yet run
unverified (harvested, no recorded run)
minkaixu/geoldm/utils.py
code served (permissive licence) · get_code("fc4da23dd75dcb46")
How it ran

no invocation recorded.

load_split_data Not yet run
unverified (harvested, no recorded run)
minkaixu/geoldm/build_geom_dataset.py
code served (permissive licence) · get_code("edf83b952680cf55")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 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 (6 with at least one paper dated earlier, 1 the same month, 8 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
unsorted_segment_sum 19 other papers
9 dated earlier, 1 the same month, 8 later, 1 same year, order not determinable · 2 only as an assembly brick
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1906.02547 (2019-06)
Combining Generative and Discriminative Models for Hybrid Inference
2102.09844 (2021-02)
E(n) Equivariant Graph Neural Networks
and 16 more not named here
sum_except_batch 6 other papers
2 dated earlier, 4 later
2105.09016 (2021-05)
E(n) Equivariant Normalizing Flows
2203.17003 (2022-03)
Equivariant Diffusion for Molecule Generation in 3D
2407.16193 (2024-07)
Test-Time Adaptation for 3D Point Clouds via Diffusion-Guided Geometric Transformation
and 3 more not named here
compute_loss_and_nll 4 other papers
1 dated earlier, 3 later
2203.17003 (2022-03)
Equivariant Diffusion for Molecule Generation in 3D
2410.06262 (2024-10)
SymDiff: Equivariant Diffusion via Stochastic Symmetrisation
2410.06502 (2024-10)
Chemistry-Inspired Diffusion with Non-Differentiable Guidance
and 1 more not named here
get_args_gen 4 other papers
1 dated earlier, 3 later
2203.17003 (2022-03)
Equivariant Diffusion for Molecule Generation in 3D
2410.06262 (2024-10)
SymDiff: Equivariant Diffusion via Stochastic Symmetrisation
2410.06502 (2024-10)
Chemistry-Inspired Diffusion with Non-Differentiable Guidance
and 1 more not named here
load_split_data 3 other papers
1 dated earlier, 1 later, 1 same year, order not determinable
2203.17003 (2022-03)
Equivariant Diffusion for Molecule Generation in 3D
aaai_25639 (2023 (year only))
MDM: Molecular Diffusion Model for 3D Molecule Generation
2410.06502 (2024-10)
Chemistry-Inspired Diffusion with Non-Differentiable Guidance
get_dataset_info 2 other papers
1 dated earlier, 1 later
2304.06174 (2023-04)
Accurate transition state generation with an object-aware equivariant elementary reaction diffusion model
2410.06262 (2024-10)
SymDiff: Equivariant Diffusion via Stochastic Symmetrisation
load_model 1 other paper
1 later
2410.06262 (2024-10)
SymDiff: Equivariant Diffusion via Stochastic Symmetrisation
random_rotation 1 other paper
1 later
2410.06262 (2024-10)
SymDiff: Equivariant Diffusion via Stochastic Symmetrisation

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

Generative models, especially diffusion models (DMs), have achieved promising results for generating feature-rich geometries and advancing foundational science problems such as molecule design. Inspired by the recent huge success of Stable (latent) Diffusion models, we propose a novel and principled method for 3D molecule generation named Geometric Latent Diffusion Models (GEOLDM). GEOLDM is the first latent DM model for the molecular geometry domain, composed of autoencoders encoding structures into continuous latent codes and DMs operating in the latent space. Our key innovation is that for modeling the 3D molecular geometries, we capture its critical roto-translational equivariance constraints by building a point-structured latent space with both invariant scalars and equivariant tensors. Extensive experiments demonstrate that GEOLDM can consistently achieve better performance on multiple molecule generation benchmarks, with up to 7% improvement for the valid percentage of large biomolecules. Results also demonstrate GEOLDM's higher capacity for controllable generation thanks to the latent modeling. Code is provided at https: //github.com/MinkaiXu/GeoLDM.

For agents

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

get_harvested_code_for_paper("2305.01140")
get_code_for_paper("2305.01140")
have("2305.01140")

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

curl https://syntology.ai/api/ran/2305.01140.json

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

[![Syntology run record](https://syntology.ai/api/ran/2305.01140.svg)](https://syntology.ai/paper/2305.01140)

Connect an agent — have() is free.