SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.10700 · 2024

Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection

arXiv · PDF · Open in the Atlas

Code that ran

7 of 10 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 0 have no contract verdict; 7 failures of our instrument; 3 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/2406.10700.json · badge: /api/ran/2406.10700.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
gwenzhang/voxel-mamba canonical (classifier label)
classifier basis: census
7 ran · 3 no recorded run
FunctionStatusWhere it lives
get_hilbert_index_2d_mamba_lite Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
gwenzhang/voxel-mamba/pcdet/models/model_utils/voxel_mamba_utils.py
code served (permissive licence) · get_code("992f09f880c252a5")
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 dict. 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)

# The function uses:
# - template: indexed with flat_coors (long tensor), should return values that can be sorted
# - coors: tensor with shape (n_points, 4) where coors[:, 0] is batch index, coors[:, 2] is y, coors[:, 3] is x
# - batch_size: integer for number of batches
# - hilbert_spatial_size: list/tuple with 3 elements [z, y, x]
# - shift: tuple with 2 elements (shift_z, shift_y) - note: used as shift[0] for y and shift[1] for x
# - debug: boolean flag

# Create a small template (Hilbert curve lookup table)
# For 2D Hilbert curve with size 4x5, we need 4*5=20 entries
hil_size_y = 4
hil_size_x = 5
template = torch.randperm(hil_size_y * hil_size_x).float()

# Create coordinates tensor
# Shape: (n_points, 4) where column 0 is batch_id, 1 is z, 2 is y, 3 is x
n_points = 8
batch_size = 2
coors = torch.tensor([
    [0, 0, 1, 2],  # batch 0
    [0, 0, 2, 3],  # batch 0
    [0, 0, 3, 1],  # batch 0
    [0, 0, 1, 4],  # batch 0
    [1, 0, 0, 0],  # batch 1
    [1, 0, 1, 1],  # batch 1
    [1, 0, 2, 2],  # batch 1
    [1, 0, 3, 3],  # batch 1
], dtype=torch.long)

hilbert_spatial_size = [3, hil_size_y, hil_size_x]
shift = (0, 1)  # (shift_z, shift_y)

ARGS = {
    'template': template,
    'coors': coors,
    'batch_size': batch_size,
    'hilbert_spatial_size': hilbert_spatial_size,
    'shift': shift,
    'debug': True,
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_hilbert_index_3d_mamba_lite Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
gwenzhang/voxel-mamba/pcdet/models/model_utils/voxel_mamba_utils.py
code served (permissive licence) · get_code("b54b5bd51a6e1d22")
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 dict. 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)

# Create a template tensor - this is a lookup table for Hilbert curve indices
# Shape should be [z_dim * y_dim * x_dim] to map flattened 3D coordinates to Hilbert indices
hilbert_spatial_size = [4, 5, 6]  # [z, y, x]
hil_size_z, hil_size_y, hil_size_x = hilbert_spatial_size
total_voxels = hil_size_z * hil_size_y * hil_size_x
template = torch.arange(total_voxels, dtype=torch.long)

# Create coordinates tensor
# Shape: (num_points, 4) where columns are [batch_idx, z, y, x]
# We'll create 12 points across 2 batches
batch_size = 2
num_points = 12
coors = torch.tensor([
    [0, 1, 2, 3],
    [0, 2, 1, 4],
    [0, 3, 2, 2],
    [0, 0, 4, 5],
    [0, 1, 3, 1],
    [0, 2, 0, 3],
    [1, 1, 1, 1],
    [1, 2, 3, 4],
    [1, 0, 2, 2],
    [1, 3, 1, 5],
    [1, 1, 4, 0],
    [1, 2, 2, 3],
], dtype=torch.long)

z_dim = 4
shift = (0, 0, 0)

ARGS = {
    'template': template,
    'coors': coors,
    'batch_size': batch_size,
    'z_dim': z_dim,
    'hilbert_spatial_size': hilbert_spatial_size,
    'shift': shift,
    'debug': True,
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
layer_norm_ref Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
gwenzhang/voxel-mamba/mamba/mamba_ssm/ops/triton/layernorm.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from XsChen524/mode-mamba-ts, is pointer only (licence: NONE) · get_code("2ce8fcf5bedd19ec")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from XsChen524/mode-mamba-ts, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

modify_logit_for_repetition_penalty Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
gwenzhang/voxel-mamba/mamba/mamba_ssm/utils/generation.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from XsChen524/mode-mamba-ts, is pointer only (licence: NONE) · get_code("da95e9a7906f3d52")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from XsChen524/mode-mamba-ts, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

rms_norm_ref Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
gwenzhang/voxel-mamba/mamba/mamba_ssm/ops/triton/layernorm.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from XsChen524/mode-mamba-ts, is pointer only (licence: NONE) · get_code("ab802ae3195c6316")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from XsChen524/mode-mamba-ts, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

sample Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
gwenzhang/voxel-mamba/mamba/mamba_ssm/utils/generation.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from XsChen524/mode-mamba-ts, is pointer only (licence: NONE) · get_code("8eafd3cf90152c82")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from XsChen524/mode-mamba-ts, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

selective_scan_ref Ran
ran; our contract draft was wrong, not the code
gwenzhang/voxel-mamba/mamba/mamba_ssm/ops/selective_scan_interface.py
code served (permissive licence) · get_code("ba7b868fec181b57")
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 3, dtype family float, shape (2, 4, 5) 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.functional as F

torch.manual_seed(0)

# Define dimensions
batch = 2
dim = 4
dstate = 3
seq_len = 5

# u: r(B D L) - input
u = torch.randn(batch, dim, seq_len)

# delta: r(B D L) - delta values
delta = torch.randn(batch, dim, seq_len)

# A: c(D N) or r(D N) - state transition matrix
A = torch.randn(dim, dstate)

# B: c(D N) or r(B N L) or r(B N 2L) or r(B G N L) or (B G N L)
# Using r(B N L) form
B = torch.randn(batch, dstate, seq_len)

# C: c(D N) or r(B N L) or r(B N 2L) or r(B G N L) or (B G N L)
# Using r(B N L) form
C = torch.randn(batch, dstate, seq_len)

# D: r(D) - optional feedthrough
D = torch.randn(dim)

# z: r(B D L) - optional gating
z = torch.randn(batch, dim, seq_len)

# delta_bias: r(D), fp32
delta_bias = torch.randn(dim, dtype=torch.float32)

# delta_softplus: bool
delta_softplus = False

# return_last_state: bool
return_last_state = False

ARGS = {
    "u": u,
    "delta": delta,
    "A": A,
    "B": B,
    "C": C,
    "D": D,
    "z": z,
    "delta_bias": delta_bias,
    "delta_softplus": delta_softplus,
    "return_last_state": return_last_state,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
einops, 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, 5) — shape (2, 4, 5) 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
decode Not yet run
unverified (harvested, no recorded run)
gwenzhang/voxel-mamba/mamba/mamba_ssm/utils/generation.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from XsChen524/mode-mamba-ts, is pointer only (licence: NONE) · get_code("eda7b73324d5e67e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from XsChen524/mode-mamba-ts, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

load_config_hf Not yet run
unverified (harvested, no recorded run)
gwenzhang/voxel-mamba/mamba/mamba_ssm/utils/hf.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from XsChen524/mode-mamba-ts, is pointer only (licence: NONE) · get_code("7a8ab4bf37f8fa41")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from XsChen524/mode-mamba-ts, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

load_state_dict_hf Not yet run
unverified (harvested, no recorded run)
gwenzhang/voxel-mamba/mamba/mamba_ssm/utils/hf.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from XsChen524/mode-mamba-ts, is pointer only (licence: NONE) · get_code("70607b36f7d19351")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from XsChen524/mode-mamba-ts, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 8 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 6 the same month, 8 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

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

FunctionAlso present inEarliest-datedOthers named
selective_scan_ref 13 other papers
6 dated earlier, 1 the same month, 6 later
2101.03961 (2021-01)
Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
2402.05608 (2024-02)
Scalable Diffusion Models with State Space Backbone
2403.16899 (2024-03)
State Space Models as Foundation Models: A Control Theoretic Overview
and 10 more not named here
layer_norm_ref 8 other papers
1 dated earlier, 2 the same month, 5 later
2403.16899 (2024-03)
State Space Models as Foundation Models: A Control Theoretic Overview
2406.02528 (2024-06)
Scalable MatMul-free Language Modeling
2406.03344 (2024-06)
Audio Mamba: Bidirectional State Space Model for Audio Representation Learning
and 5 more not named here
rms_norm_ref 8 other papers
1 dated earlier, 2 the same month, 5 later
2403.16899 (2024-03)
State Space Models as Foundation Models: A Control Theoretic Overview
2406.02528 (2024-06)
Scalable MatMul-free Language Modeling
2406.03344 (2024-06)
Audio Mamba: Bidirectional State Space Model for Audio Representation Learning
and 5 more not named here
modify_logit_for_repetition_penalty 6 other papers
1 dated earlier, 1 the same month, 4 later
2403.16899 (2024-03)
State Space Models as Foundation Models: A Control Theoretic Overview
2406.03344 (2024-06)
Audio Mamba: Bidirectional State Space Model for Audio Representation Learning
2407.06136 (2024-07)
Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning
and 3 more not named here
load_config_hf 5 other papers
1 dated earlier, 1 the same month, 3 later
2403.16899 (2024-03)
State Space Models as Foundation Models: A Control Theoretic Overview
2406.03344 (2024-06)
Audio Mamba: Bidirectional State Space Model for Audio Representation Learning
2407.06136 (2024-07)
Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning
and 2 more not named here
load_state_dict_hf 4 other papers
1 dated earlier, 1 the same month, 2 later
2403.16899 (2024-03)
State Space Models as Foundation Models: A Control Theoretic Overview
2406.03344 (2024-06)
Audio Mamba: Bidirectional State Space Model for Audio Representation Learning
2407.06136 (2024-07)
Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning
and 1 more not named here
sample 4 other papers
1 dated earlier, 3 later
2403.16899 (2024-03)
State Space Models as Foundation Models: A Control Theoretic Overview
2407.06136 (2024-07)
Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning
2408.15237 (2024-08)
The Mamba in the Llama: Distilling and Accelerating Hybrid Models
and 1 more not named here
decode 3 other papers
1 dated earlier, 2 later
2403.16899 (2024-03)
State Space Models as Foundation Models: A Control Theoretic Overview
2407.06136 (2024-07)
Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning
2601.00920 (2026-01)
MODE: Efficient Time Series Prediction with Mamba Enhanced by Low-Rank Neural ODEs

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

Serialization-based methods, which serialize the 3D voxels and group them into multiple sequences before inputting to Transformers, have demonstrated their effectiveness in 3D object detection. However, serializing 3D voxels into 1D sequences will inevitably sacrifice the voxel spatial proximity. Such an issue is hard to be addressed by enlarging the group size with existing serialization-based methods due to the quadratic complexity of Transformers with feature sizes. Inspired by the recent advances of state space models (SSMs), we present a Voxel SSM, termed as Voxel Mamba, which employs a group-free strategy to serialize the whole space of voxels into a single sequence. The linear complexity of SSMs encourages our group-free design, alleviating the loss of spatial proximity of voxels. To further enhance the spatial proximity, we propose a Dual-scale SSM Block to establish a hierarchical structure, enabling a larger receptive field in the 1D serialization curve, as well as more complete local regions in 3D space. Moreover, we implicitly apply window partition under the group-free framework by positional encoding, which further enhances spatial proximity by encoding voxel positional information. Our experiments on Waymo Open Dataset and nuScenes dataset show that Voxel Mamba not only achieves higher accuracy than state-of-the-art methods, but also demonstrates significant advantages in computational efficiency.

For agents

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

get_harvested_code_for_paper("2406.10700")
get_code_for_paper("2406.10700")
have("2406.10700")

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

curl https://syntology.ai/api/ran/2406.10700.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.10700.svg)](https://syntology.ai/paper/2406.10700)

Connect an agent — have() is free.