SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2502.02150 · ICML · 2025

On the Guidance of Flow Matching

Tailin Wu, Ruiqi Feng, Peiyan Hu, Chenglei Yu, Wenhao Deng

arXiv · PDF · Open in the Atlas

Code that ran

11 of 13 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; 3 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 3 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/2502.02150.json · badge: /api/ran/2502.02150.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
ai4science-westlakeu/flow_guidance canonical (classifier label)
classifier basis not recorded on the link
11 ran · 2 no recorded run
FunctionStatusWhere it lives
apply_conditioning Ran
ran; our contract draft was wrong, not the code
ai4science-westlakeu/flow_guidance/offline_rl/gflower/models_flow/flow_matcher.py
code served (permissive licence) · get_code("b3d593fb33f79ac5")
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, 5, 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 as nn

torch.manual_seed(0)

# x: tensor that will be indexed and have values assigned
# The function indexes x[:, t, action_dim:] where t comes from conditions.keys()
# and assigns val.clone() to it
# So x needs shape (batch_size, time_steps, feature_dim)
# with feature_dim > action_dim
batch_size = 2
time_steps = 5
action_dim = 2
feature_dim = 4  # must be > action_dim

x = torch.randn(batch_size, time_steps, feature_dim)

# conditions: dict mapping timestep t to a tensor val
# The function does x[:, t, action_dim:] = val.clone()
# So val should have shape (batch_size, feature_dim - action_dim)
condition_shape = (batch_size, feature_dim - action_dim)
conditions = {
    1: torch.randn(condition_shape),
    3: torch.randn(condition_shape),
}

ARGS = {
    "x": x,
    "conditions": conditions,
    "action_dim": action_dim,
}
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 3, dtype family float, shape (2, 5, 4) — shape (2, 5, 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
apply_conditioning_from_conditioned_x Ran
ran on a synthesized input
ai4science-westlakeu/flow_guidance/offline_rl/gflower/models_flow/flow_matcher.py
code served (permissive licence) · get_code("4e3580c79a7f3448")
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, 5, 7) 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 small tensors with distinct dimensions
# x: (batch=2, time=5, features=7) where features = action_dim(3) + state(4)
batch_size = 2
time_steps = 5
action_dim = 3
state_dim = 4
total_features = action_dim + state_dim

x = torch.randn(batch_size, time_steps, total_features)
x_conditioned = torch.randn(batch_size, time_steps, total_features)

# conditions: dict mapping time indices to values
# The function iterates over conditions.items() and uses t as an index
conditions = {
    0: torch.randn(batch_size, total_features),
    2: torch.randn(batch_size, total_features),
    4: torch.randn(batch_size, total_features),
}

ARGS = {
    "x": x,
    "x_conditioned": x_conditioned,
    "conditions": conditions,
    "action_dim": action_dim,
}
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 3, dtype family float, shape (2, 5, 7) — shape (2, 5, 7) 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
contrastive_energy_loss Ran
ran on a synthesized input
ai4science-westlakeu/flow_guidance/synthetic/guided_flow/guidance/contrastive_energy.py
code served (permissive licence) · get_code("0805a4fb5d3550c2")
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)

# Define a simple model that takes concatenated input and outputs energy scores
class EnergyModel(nn.Module):
    def __init__(self, input_dim, output_dim):
        super().__init__()
        self.linear = nn.Linear(input_dim, output_dim)
    
    def forward(self, x):
        return self.linear(x)

# Define a simple J function (callable) that computes energy
class JFunction:
    def __call__(self, x):
        # x has shape (batch_size, feature_dim)
        # Return energy scores of shape (batch_size,)
        return torch.sum(x, dim=1)

# Create model: takes concatenated [xt, t] as input
# xt is (2, 4), t is (2, 1), so concatenated is (2, 5)
# Output should be (2,) for softmax over batch
model = EnergyModel(input_dim=5, output_dim=2)

# Create J function
J = JFunction()

# Create beta parameter (scalar)
beta = 1.0

# Create xt tensor: batch size 2, feature dim 4
xt = torch.randn(2, 4)

# Create t tensor: batch size 2 (will be expanded to 2x1)
t = torch.randn(2)

ARGS = {
    "model": model,
    "beta": beta,
    "J": J,
    "xt": xt,
    "t": t,
}
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
cosine_beta_schedule Ran
ran, honoured the contract we drafted
ai4science-westlakeu/flow_guidance/offline_rl/gflower/models_flow/helpers.py
code served (permissive licence) · get_code("b6113e0f43155a33")
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 (10,) 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
import torch

torch.manual_seed(0)

ARGS = {
    "timesteps": 10,
    "s": 0.008,
    "dtype": torch.float32,
}
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 1, dtype family float, shape (10,) — shape (10,) 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
cosine_beta_schedule Ran
ran, honoured the contract we drafted
ai4science-westlakeu/flow_guidance/offline_rl/gflower/models_flow/unet.py
code served (permissive licence) · get_code("a46ae414f0327ebd")
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 (10,) 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 = {
    "timesteps": 10,
    "s": 0.008,
    "dtype": torch.float32,
}
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 1, dtype family float, shape (10,) — shape (10,) 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_2d_sincos_pos_embed Ran
ran, honoured the contract we drafted
ai4science-westlakeu/flow_guidance/offline_rl/gflower/models_flow/transformer.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
modulate Ran
ran; our contract draft was wrong, not the code
ai4science-westlakeu/flow_guidance/offline_rl/gflower/models_flow/transformer.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
pad_t_like_x Ran
ran; our contract draft was wrong, not the code
ai4science-westlakeu/flow_guidance/offline_rl/gflower/models_flow/flow_matcher.py
code served (permissive licence) · get_code("9e320fdaa5a3063f")
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 4, dtype family float, shape (2, 1, 1, 1) 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 a batch of 2 samples with 3 channels, width 4, height 5
x = torch.randn(2, 3, 4, 5)

# Create a time vector with batch size 2
t = torch.randn(2)

ARGS = {
    't': t,
    'x': x
}
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 4, dtype family float, shape (2, 1, 1, 1) — shape (2, 1, 1, 1) 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
to_np Ran
ran on a synthesized input
ai4science-westlakeu/flow_guidance/offline_rl/gflower/models_flow/flow_policy.py
code served (permissive licence) · get_code("3e55aeee1baa4767")
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 ndarray, 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)

# Test case 1: torch.Tensor
tensor_input = torch.randn(2, 4)

# Test case 2: numpy array (non-tensor)
numpy_input = np.array([1, 2, 3, 4])

# Test case 3: regular Python object
python_input = [1, 2, 3]

# The function takes a single parameter 'x' which can be either a Tensor or something else
# We'll test with a tensor as the primary case
ARGS = {
    "x": tensor_input
}
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 ndarray, 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
wasserstein Ran
ran on a synthesized input
ai4science-westlakeu/flow_guidance/offline_rl/gflower/models_flow/optimal_transport.py
code served (permissive licence) · get_code("fb64fad1227c686b")
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 float, 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 math
from functools import partial

torch.manual_seed(0)

# Create small tensors for x0 and x1
# x0: shape (bs, *dim) - batch_size=2, flattened_dim=4
x0 = torch.randn(2, 4)
# x1: shape (bs, *dim) - batch_size=2, flattened_dim=4
x1 = torch.randn(2, 4)

# method can be None, 'exact', or 'sinkhorn'
method = 'sinkhorn'

# reg is the entropic regularization coefficient
reg = 0.05

# power is 1 or 2
power = 2

ARGS = {
    'x0': x0,
    'x1': x1,
    'method': method,
    'reg': reg,
    'power': power,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
ot, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, 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
wrap_grad_fn Ran
ran on a synthesized input
ai4science-westlakeu/flow_guidance/synthetic/guided_flow/guidance/gradient_guidance.py
code served (permissive licence) · get_code("12bdc669adc8f3f5")
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
import torch.nn as nn
import math

torch.manual_seed(0)

# Create a simple model that does nothing special
class DummyModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Create a simple grad_fn that takes (t, x, dx_dt, model) and returns a tensor
def dummy_grad_fn(t, x, dx_dt, model):
    # Return a tensor with the same shape as x
    return torch.ones_like(x)

# Set up the arguments
scale = 2.5
schedule = 'cosine_decay'
grad_fn = dummy_grad_fn
eps = 0.1
model = DummyModel()

# Create sample tensors for testing the wrapped function
t = torch.tensor(0.5)
x = torch.randn(2, 4)
dx_dt = torch.randn(2, 4)

ARGS = {
    'scale': scale,
    'schedule': schedule,
    'grad_fn': grad_fn,
    'eps': eps
}
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
extract Not yet run
unverified (harvested, no recorded run)
ai4science-westlakeu/flow_guidance/offline_rl/gflower/models_flow/helpers.py
code served (permissive licence) · get_code("09c8479d9a5b3e06")
How it ran

no invocation recorded.

get_2d_sincos_pos_embed_from_grid Not yet run
unverified (harvested, no recorded run)
ai4science-westlakeu/flow_guidance/offline_rl/gflower/models_flow/transformer.py
code served (permissive licence) · get_code("665d8a4e8f673a4c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 4 the same month, 7 later) and 5 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
143 dated earlier, 2 the same month, 42 later, 3 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
67 dated earlier, 32 later, 1 same year, order not determinable, 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
extract 77 other papers
62 dated earlier, 2 the same month, 12 later, 1 same year, order not determinable · 32 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
2102.05379 (2021-02)
Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
and 74 more not named here
get_2d_sincos_pos_embed 69 other papers
48 dated earlier, 21 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
cosine_beta_schedule 20 other papers
16 dated earlier, 1 the same month, 3 later · 8 only as an assembly brick
2208.06193 (2022-08)
Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning
2210.15629 (2022-10)
Language Control Diffusion: Efficiently Scaling through Space, Time, and Tasks
2303.14676 (2023-03)
PDPP: Projected Diffusion for Procedure Planning in Instructional Videos
and 17 more not named here
apply_conditioning 9 other papers
6 dated earlier, 1 the same month, 2 later · 2 only as an assembly brick
2210.15629 (2022-10)
Language Control Diffusion: Efficiently Scaling through Space, Time, and Tasks
2305.18459 (2023-05)
Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning
2405.04235 (2024-05)
LTLDoG: Satisfying Temporally-Extended Symbolic Constraints for Safe Diffusion-based Planning
and 6 more not named here
pad_t_like_x 6 other papers
4 dated earlier, 2 later · 2 only as an assembly brick
2302.00482 (2023-02)
Improving and generalizing flow-based generative models with minibatch optimal transport
2307.03672 (2023-07)
Simulation-free Schrödinger bridges via score and flow matching
2405.15252 (2024-05)
Accelerating 3D Molecule Generation via Jointly Geometric Optimal Transport
and 3 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

Flow matching has shown state-of-the-art performance in various generative tasks, ranging from image generation to decision-making, where generation under energy guidance (abbreviated as guidance in the following) is pivotal. However, the guidance of flow matching is more general than and thus substantially different from that of its predecessor, diffusion models. Therefore, the challenge in guidance for general flow matching remains largely underexplored. In this paper, we propose the first framework of general guidance for flow matching. From this framework, we derive a family of guidance techniques that can be applied to general flow matching. These include a new training-free asymptotically exact guidance, novel training losses for training-based guidance, and two classes of approximate guidance that cover classical gradient guidance methods as special cases. We theoretically investigate these different methods to give a practical guideline for choosing suitable methods in different scenarios. Experiments on synthetic datasets, image inverse problems, and offline reinforcement learning demonstrate the effectiveness of our proposed guidance methods and verify the correctness of our flow matching guidance framework. Code to reproduce the experiments can be found at https://github. com/AI4Science-WestlakeU/flow_ guidance.

For agents

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

get_harvested_code_for_paper("2502.02150")
get_code_for_paper("2502.02150")
have("2502.02150")

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

curl https://syntology.ai/api/ran/2502.02150.json

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

[![Syntology run record](https://syntology.ai/api/ran/2502.02150.svg)](https://syntology.ai/paper/2502.02150)

Connect an agent — have() is free.