SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.08751 · NeurIPS · 2024

Latent Diffusion for Neural Spiking Data

Jaivardhan Kapoor, Jakob Macke, Auguste Schulz, Julius Vetter, Felix Pei, Richard Gao

arXiv · PDF · Open in the Atlas

Code that ran

14 of 22 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 10 failures of our instrument; 8 no recorded run), measured 2026-11-21; 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/2407.08751.json · badge: /api/ran/2407.08751.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
mackelab/LDNS canonical (classifier label)
classifier basis: classifier_2025
10 ran · 8 no recorded run
copy not recorded community
not in the paper's declared repositories
4 ran · 0 no recorded run
FunctionStatusWhere it lives
Activation Ran
ran; our contract draft was wrong, not the code
mackelab/LDNS/ldns/networks/blocks.py
code served (permissive licence) · get_code("ae5bb489492e56d4")
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 ReLU. 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

torch.manual_seed(0)

# The function takes two parameters: activation and dim
# activation can be None, string identifiers, or other values
# dim is used as a parameter to nn.GLU when activation == 'glu'

ARGS = {
    'activation': 'relu',
    'dim': -1
}
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 ReLU — a ReLU output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ReLU 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
DropoutNd Ran
ran on a synthesized input · constructed an object; no result was computed
mackelab/LDNS/ldns/networks/blocks.py
code served (permissive licence) · get_code("7b57689a78611e37")
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 an instance of its own class, DropoutNd: the run constructed the object and did not call it, so no result was computed. 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

torch.manual_seed(0)

# Create a sample input tensor
# Shape: (batch=2, dim=4, length=3) - transposed format (b, d, ...)
X = torch.randn(2, 4, 3)

ARGS = {
    'p': 0.5,
    'tie': True,
    'transposed': True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
einops, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DropoutNd — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a DropoutNd 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
Kernel Ran
ran on a synthesized input · constructed an object; no result was computed
mackelab/LDNS/ldns/networks/blocks.py
code served (permissive licence) · get_code("637ce76ea996d0da")
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 an instance of its own class, Kernel: the run constructed the object and did not call it, so no result was computed. 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 logging
from collections import defaultdict
from typing import Mapping, Optional, Tuple, Union

torch.manual_seed(0)

# The Kernel class is abstract, so we'll create a minimal concrete subclass for testing
class ConcreteKernel(nn.Module):
    """Minimal concrete implementation of Kernel for testing."""
    
    def __init__(self, d_model: int=0, channels: int=1, l_max: Optional[int]=None, lr: Union[float, Optional[Mapping]]=None, wd: Union[float, Optional[Mapping]]=0.0, verbose: bool=True, **kwargs):
        super().__init__()
        self.H = self.d_model = d_model
        self.L = self.l_max = l_max
        self.channels = channels
        self.lr = lr
        self.wd = wd
        self.verbose = verbose
        
        if self.lr is None or isinstance(self.lr, float):
            self.lr_dict = defaultdict(lambda: self.lr)
        else:
            self.lr_dict = defaultdict(lambda: None)
            self.lr_dict.update(self.lr)
        
        if self.wd is None or isinstance(self.wd, float):
            self.wd_dict = defaultdict(lambda: self.wd)
        else:
            self.wd_dict = defaultdict(lambda: None)
            self.wd_dict.update(self.wd)
    
    def forward(self, state=None, rate=1.0, L=None):
        """Minimal forward implementation."""
        if L is None:
            L = self.l_max or 10
        # Return kernel shape (C, H, L) and optional state output
        kernel = torch.randn(self.channels, self.H, L)
        return kernel
    
    def _setup_step(self, **kwargs):
        """Minimal setup for recurrent mode."""
        pass
    
    def step(self, x, state, **kwargs):
        """Minimal step for recurrent inference."""
        return x, state


# Build arguments for the Kernel.__init__ method
ARGS = {
    'd_model': 4,
    'channels': 2,
    'l_max': 10,
    'lr': 0.001,
    'wd': 0.0,
    'verbose': True,
}
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 Kernel — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Kernel 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
SSMKernel Ran
ran on a synthesized input · constructed an object; no result was computed
mackelab/LDNS/ldns/networks/blocks.py
code served (permissive licence) · get_code("7b5ca9528f2d5fed")
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 an instance of its own class, SSMKernel: the run constructed the object and did not call it, so no result was computed. 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 collections import defaultdict

torch.manual_seed(0)

# The function signature shows __init__ parameters for the Kernel class
# We need to construct valid arguments for instantiation

ARGS = {
    'd_model': 8,
    'channels': 2,
    'l_max': 128,
    'lr': 0.001,
    'wd': 0.0,
    'verbose': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
einops, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SSMKernel — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a SSMKernel 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
cauchy_naive Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from state-spaces/s4
pointer only · get_code("b7d9d94554e93b1b")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

dplr Ran
ran; our contract draft was wrong, not the code
mackelab/LDNS/ldns/networks/blocks.py
code served (permissive licence) · get_code("64f3b90fc3deaa09")
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 numpy as np

torch.manual_seed(0)

ARGS = {
    'init': 'hippo',
    'N': 64,
    'rank': 1,
    'H': 1,
    'dtype': torch.float,
    'real_random': False,
    'real_scale': 1.0,
    'imag_random': False,
    'imag_scale': 1.0,
    'B_random': False,
    'B_init': 'constant',
    'B_scale': 1.0,
    'P_scale': 1.0,
    'normalize': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
einops, numpy, 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
get_logger Ran
ran; our contract draft was wrong, not the code
mackelab/LDNS/ldns/networks/blocks.py
code served (permissive licence) · get_code("0fa25f334c0ad357")
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 Logger. 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 logging

ARGS = {
    "name": "test_logger",
    "level": logging.INFO,
}
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 Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger 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
inv_transform Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from weitunglin/pixmamba
pointer only; the stored copy get_code serves, from weitunglin/pixmamba, is pointer only (licence: NONE) · get_code("26b8695dba83b816")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

log_vandermonde_naive Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from state-spaces/s4
pointer only · get_code("e25911109ba29783")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

nplr Ran
ran; our contract draft was wrong, not the code
mackelab/LDNS/ldns/networks/blocks.py
code served (permissive licence) · get_code("a8f4e0bd6f8bebf5")
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 numpy as np

torch.manual_seed(0)

ARGS = {
    'measure': 'legs',
    'N': 4,
    'rank': 1,
    'dtype': torch.float,
    'diagonalize_precision': True,
    'B_clip': 2.0,
}
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 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
param_transform Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from weitunglin/pixmamba
pointer only; the stored copy get_code serves, from weitunglin/pixmamba, is pointer only (licence: NONE) · get_code("6f7ad7d857dc0d1e")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

power Ran
ran; our contract draft was wrong, not the code
mackelab/LDNS/ldns/networks/blocks.py
code served (permissive licence) · get_code("8e0326e9fa719a59")
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 numpy as np
from einops import rearrange, repeat

torch.manual_seed(0)

# Construct arguments for the power function
# A: (..., N, N) - a square matrix
# v: (..., N, L) - optional vector for scan computation
# L: exponent for matrix power

# Create a small square matrix A with shape (4, 4)
A = torch.randn(4, 4)

# Create v with shape (4, 8) where N=4 and L=8
v = torch.randn(4, 8)

# L is the exponent
L = 8

ARGS = {
    "L": L,
    "A": A,
    "v": v,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
einops, numpy, 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
rank_correction Ran
ran, honoured the contract we drafted
mackelab/LDNS/ldns/networks/blocks.py
code served (permissive licence) · get_code("3eab4e035dc5c1f0")
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 (1, 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)

ARGS = {
    'measure': 'legs',
    'N': 4,
    'rank': 1,
    'dtype': torch.float,
}
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 2, dtype family float, shape (1, 4) — shape (1, 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
transition Ran
ran; our contract draft was wrong, not the code
mackelab/LDNS/ldns/networks/blocks.py
code served (permissive licence) · get_code("fe900ba398d10d9d")
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 numpy as np

ARGS = {
    'measure': 'legt',
    'N': 4,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — 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
AutoEncoder Not yet run
unverified (harvested, no recorded run)
mackelab/LDNS/ldns/networks/blocks.py
code served (permissive licence) · get_code("3d1d5f57adee63ba")
How it ran

no invocation recorded.

AutoEncoderBlock Not yet run
unverified (harvested, no recorded run)
mackelab/LDNS/ldns/networks/blocks.py
code served (permissive licence) · get_code("dc835e940474f275")
How it ran

no invocation recorded.

FFTConv Not yet run
unverified (harvested, no recorded run)
mackelab/LDNS/ldns/networks/blocks.py
code served (permissive licence) · get_code("3a7289b23b9cff26")
How it ran

no invocation recorded.

SSMKernelDPLR Not yet run
unverified (harvested, no recorded run)
mackelab/LDNS/ldns/networks/blocks.py
code served (permissive licence) · get_code("ab17757609d5a3a7")
How it ran

no invocation recorded.

SSMKernelDiag Not yet run
unverified (harvested, no recorded run)
mackelab/LDNS/ldns/networks/blocks.py
code served (permissive licence) · get_code("742bff484ed96eec")
How it ran

no invocation recorded.

combination Not yet run
unverified (harvested, no recorded run)
mackelab/LDNS/ldns/networks/blocks.py
code served (permissive licence) · get_code("03eeb2985cde61ff")
How it ran

no invocation recorded.

log_vandermonde_transpose_naive Not yet run
unverified (harvested, no recorded run)
mackelab/LDNS/ldns/networks/blocks.py
code served (permissive licence) · get_code("7cfca855faa8e8dc")
How it ran

no invocation recorded.

ssm Not yet run
unverified (harvested, no recorded run)
mackelab/LDNS/ldns/networks/blocks.py
code served (permissive licence) · get_code("154cc10f3036f3c6")
How it ran

no invocation recorded.

Also present in other papers' code

Of 22 samples lifted from this paper's linked repositories, 22 carry a function identity and 0 do not. Of the 22 distinct functions with an identity, 17 are also present in other papers whose code we hold (17 with at least one paper dated earlier, 0 the same month, 2 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
cauchy_naive
brick of this paper's assembly: helper
6 other papers
5 dated earlier, 1 later · 1 only as an assembly brick
1612.00796 (2016-12)
Overcoming catastrophic forgetting in neural networks
2111.00396 (2021-11)
Efficiently Modeling Long Sequences with Structured State Spaces
2312.00752 (2023-12)
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
and 3 more not named here
log_vandermonde_naive
brick of this paper's assembly: helper
6 other papers
5 dated earlier, 1 later · 1 only as an assembly brick
1612.00796 (2016-12)
Overcoming catastrophic forgetting in neural networks
2111.00396 (2021-11)
Efficiently Modeling Long Sequences with Structured State Spaces
2312.00752 (2023-12)
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
and 3 more not named here
log_vandermonde_transpose_naive
brick of this paper's assembly: helper
4 other papers
4 dated earlier · 2 only as an assembly brick
1612.00796 (2016-12)
Overcoming catastrophic forgetting in neural networks
2111.00396 (2021-11)
Efficiently Modeling Long Sequences with Structured State Spaces
2312.00752 (2023-12)
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
and 1 more not named here
get_logger
brick of this paper's assembly: helper
3 other papers
3 dated earlier · 1 only as an assembly brick
1312.5602 (2013-12)
Playing Atari with Deep Reinforcement Learning
2022.findings-emnlp.242 (2022 (year only))
ER-TEST: Evaluating Explanation Regularization Methods for Language Models
2210.09337 (2022-10)
Robust Imitation of a Few Demonstrations with a Backwards Model
inv_transform
brick of this paper's assembly: helper
3 other papers
3 dated earlier · 2 only as an assembly brick
2111.00396 (2021-11)
Efficiently Modeling Long Sequences with Structured State Spaces
2312.00752 (2023-12)
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
2402.02491 (2024-02)
VM-UNet: Vision Mamba UNet for Medical Image Segmentation
param_transform
brick of this paper's assembly: helper
3 other papers
3 dated earlier · 2 only as an assembly brick
2111.00396 (2021-11)
Efficiently Modeling Long Sequences with Structured State Spaces
2312.00752 (2023-12)
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
2402.02491 (2024-02)
VM-UNet: Vision Mamba UNet for Medical Image Segmentation
DropoutNd
brick of this paper's assembly: helper
2 other papers
2 dated earlier · 2 only as an assembly brick
2111.00396 (2021-11)
Efficiently Modeling Long Sequences with Structured State Spaces
2312.00752 (2023-12)
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
Kernel
brick of this paper's assembly: helper
2 other papers
2 dated earlier
2111.00396 (2021-11)
Efficiently Modeling Long Sequences with Structured State Spaces
2312.00752 (2023-12)
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
SSMKernel
brick of this paper's assembly: helper
2 other papers
2 dated earlier
2111.00396 (2021-11)
Efficiently Modeling Long Sequences with Structured State Spaces
2312.00752 (2023-12)
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
combination
brick of this paper's assembly: helper
2 other papers
2 dated earlier
2111.00396 (2021-11)
Efficiently Modeling Long Sequences with Structured State Spaces
2312.00752 (2023-12)
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
dplr
brick of this paper's assembly: helper
2 other papers
2 dated earlier
2111.00396 (2021-11)
Efficiently Modeling Long Sequences with Structured State Spaces
2312.00752 (2023-12)
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
nplr
brick of this paper's assembly: helper
2 other papers
2 dated earlier · 1 only as an assembly brick
2111.00396 (2021-11)
Efficiently Modeling Long Sequences with Structured State Spaces
2312.00752 (2023-12)
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
power
brick of this paper's assembly: helper
2 other papers
2 dated earlier · 2 only as an assembly brick
2111.00396 (2021-11)
Efficiently Modeling Long Sequences with Structured State Spaces
2312.00752 (2023-12)
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
rank_correction
brick of this paper's assembly: helper
2 other papers
2 dated earlier · 2 only as an assembly brick
2111.00396 (2021-11)
Efficiently Modeling Long Sequences with Structured State Spaces
2312.00752 (2023-12)
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
ssm
brick of this paper's assembly: helper
2 other papers
2 dated earlier
2111.00396 (2021-11)
Efficiently Modeling Long Sequences with Structured State Spaces
2312.00752 (2023-12)
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
transition
brick of this paper's assembly: helper
2 other papers
2 dated earlier · 2 only as an assembly brick
2111.00396 (2021-11)
Efficiently Modeling Long Sequences with Structured State Spaces
2312.00752 (2023-12)
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
Activation
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2312.00752 (2023-12)
Mamba: Linear-Time Sequence Modeling with Selective State Spaces

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Modern datasets in neuroscience enable unprecedented inquiries into the relationship between complex behaviors and the activity of many simultaneously recorded neurons. While latent variable models can successfully extract low-dimensional embeddings from such recordings, using them to generate realistic spiking data, especially in a behavior-dependent manner, still poses a challenge. Here, we present Latent Diffusion for Neural Spiking data (LDNS), a diffusion-based generative model with a low-dimensional latent space: LDNS employs an autoencoder with structured state-space (S4) layers to project discrete high-dimensional spiking data into continuous time-aligned latents. On these inferred latents, we train expressive (conditional) diffusion models, enabling us to sample neural activity with realistic single-neuron and population spiking statistics. We validate LDNS on synthetic data, accurately recovering latent structure, firing rates, and spiking statistics. Next, we demonstrate its flexibility by generating variable-length data that mimics human cortical activity during attempted speech. We show how to equip LDNS with an expressive observation model that accounts for single-neuron dynamics not mediated by the latent state, further increasing the realism of generated samples. Finally, conditional LDNS trained on motor cortical activity during diverse reaching behaviors can generate realistic spiking data given reach direction or unseen reach trajectories. In summary, LDNS simultaneously enables inference of low-dimensional latents and realistic conditional generation of neural spiking datasets, opening up further possibilities for simulating experimentally testable hypotheses.

For agents

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

get_harvested_code_for_paper("2407.08751")
get_code_for_paper("2407.08751")
have("2407.08751")

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

curl https://syntology.ai/api/ran/2407.08751.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.08751.svg)](https://syntology.ai/paper/2407.08751)

Connect an agent — have() is free.