SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · Xie_PVMamba_Parallelizing_Vision_Mamba_via_Dynamic_State_Aggregation_ICCV_2025_paper · ICCV · 2025

PVMamba: Parallelizing Vision Mamba via Dynamic State Aggregation

Chao Ma, Zhongdao Wang, Weijia Zhang, Fei Xie

Open in the Atlas

Code that ran

12 of 15 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, 1 violated it and 0 have no contract verdict; 8 failures of our instrument; 3 no recorded run), measured 2026-11-22; 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/Xie_PVMamba_Parallelizing_Vision_Mamba_via_Dynamic_State_Aggregation_ICCV_2025_paper.json · badge: /api/ran/Xie_PVMamba_Parallelizing_Vision_Mamba_via_Dynamic_State_Aggregation_ICCV_2025_paper.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
VISION-SJTU/PVMamba canonical (classifier label)
classifier basis: census
12 ran · 3 no recorded run
FunctionStatusWhere it lives
auto_resume_helper Ran
ran; our contract draft was wrong, not the code
VISION-SJTU/PVMamba/classification/utils/utils.py
code served (permissive licence) · get_code("1f9f75e583e2169e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import torch
import tempfile
import shutil

torch.manual_seed(0)

# Create a temporary directory with test checkpoint files
temp_dir = tempfile.mkdtemp()

# Create a valid checkpoint file
valid_checkpoint = {
    'model_state_dict': torch.randn(2, 4),
    'optimizer_state_dict': torch.randn(3, 5),
    'epoch': 1
}
valid_ckpt_path = os.path.join(temp_dir, 'checkpoint_001.pth')
torch.save(valid_checkpoint, valid_ckpt_path)

# Create an invalid checkpoint file (will fail to load)
invalid_ckpt_path = os.path.join(temp_dir, 'checkpoint_002.pth')
with open(invalid_ckpt_path, 'w') as f:
    f.write('invalid checkpoint content')

# Create another valid checkpoint file (newer, should be picked first)
valid_checkpoint_2 = {
    'model_state_dict': torch.randn(2, 4),
    'epoch': 2
}
valid_ckpt_path_2 = os.path.join(temp_dir, 'checkpoint_003.pth')
torch.save(valid_checkpoint_2, valid_ckpt_path_2)

# Ensure checkpoint_003 is newer than checkpoint_001
os.utime(valid_ckpt_path_2, None)

ARGS = {
    'output_dir': temp_dir
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
build_optimizer Ran
ran; our contract draft was wrong, not the code
VISION-SJTU/PVMamba/classification/utils/optimizer.py
code served (permissive licence) · get_code("00fc7f0336e999a0")
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 AdamW. 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 import optim
from unittest.mock import MagicMock

torch.manual_seed(0)

# Create a minimal model with parameters
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.bn = nn.BatchNorm1d(3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.bn(x)
        x = self.linear2(x)
        return x

model = SimpleModel()

# Create a config object with all required attributes
class Config:
    class Train:
        class Optimizer:
            NAME = 'adamw'
            MOMENTUM = 0.9
            EPS = 1e-8
            BETAS = (0.9, 0.999)
        
        OPTIMIZER = Optimizer()
        BASE_LR = 0.001
        WEIGHT_DECAY = 0.0001
    
    TRAIN = Train()

config = Config()

# Create a mock logger
logger = MagicMock()
logger.info = MagicMock()

ARGS = {
    'config': config,
    'model': model,
    'logger': logger
}
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 AdamW — a AdamW output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a AdamW 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
build_scheduler Ran
ran; our contract draft was wrong, not the code
VISION-SJTU/PVMamba/classification/utils/lr_scheduler.py
code served (permissive licence) · get_code("0fbdf3257aea9bcc")
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 LinearLRScheduler. 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 torch.optim as optim
from types import SimpleNamespace

torch.manual_seed(0)

# Create a minimal model for the optimizer
model = nn.Linear(4, 3)

# Create an optimizer
optimizer = optim.SGD(model.parameters(), lr=0.1)

# Create a minimal config object with all required attributes
config = SimpleNamespace(
    TRAIN=SimpleNamespace(
        EPOCHS=10,
        WARMUP_EPOCHS=2,
        WARMUP_LR=0.0,
        MIN_LR=0.00001,
        LR_SCHEDULER=SimpleNamespace(
            NAME='linear',
            DECAY_EPOCHS=5,
            DECAY_RATE=0.1,
            GAMMA=0.1,
            WARMUP_PREFIX=False,
            MULTISTEPS=[3, 6, 9]
        )
    )
)

# n_iter_per_epoch parameter
n_iter_per_epoch = 100

ARGS = {
    'config': config,
    'optimizer': optimizer,
    'n_iter_per_epoch': n_iter_per_epoch
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
timm, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type LinearLRScheduler — a LinearLRScheduler output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a LinearLRScheduler 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
check_keywords_in_name Ran
ran, violated the contract we drafted
VISION-SJTU/PVMamba/classification/utils/optimizer.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from leaplabthu/inline, is pointer only (licence: NONE) · get_code("b0a5beb34716d5a6")
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 leaplabthu/inline, 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.

create_logger Ran
ran; our contract draft was wrong, not the code
VISION-SJTU/PVMamba/classification/utils/logger.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from ghrua/seqpe, is pointer only (licence: NONE) · get_code("80450600f7f09b0a")
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 ghrua/seqpe, 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.

flops_selective_scan_fn Ran
ran, honoured the contract we drafted
VISION-SJTU/PVMamba/classification/models/utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from daidaijr/EAMamba, is pointer only (licence: NONE) · get_code("da1a64838a2535e5")
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 daidaijr/EAMamba, 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.

flops_selective_scan_ref Ran
ran, honoured the contract we drafted
VISION-SJTU/PVMamba/classification/models/utils.py
code served (permissive licence) · get_code("0b84e99fd1e93dd6")
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 numpy as np

# ARGS dict for flops_selective_scan_ref
ARGS = {
    'B': 2,
    'L': 256,
    'D': 768,
    'N': 16,
    'with_D': True,
    'with_Z': False,
    'with_Group': True,
    'with_complex': False,
}
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 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
get_grad_norm Ran
ran, honoured the contract we drafted
VISION-SJTU/PVMamba/classification/utils/utils.py
code served (permissive licence) · get_code("eec1e7cba51d5e8e")
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 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 torch.nn as nn

torch.manual_seed(0)

# Create a simple model with parameters that have gradients
model = nn.Linear(4, 3)

# Forward pass to create some gradients
x = torch.randn(2, 4)
y = model(x)
loss = y.sum()
loss.backward()

# Now model.parameters() have gradients attached
parameters = list(model.parameters())

ARGS = {
    "parameters": parameters,
    "norm_type": 2
}
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 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
import_abspy Ran
ran; our contract draft was wrong, not the code
VISION-SJTU/PVMamba/segmentation/model.py
code served (permissive licence) · get_code("5315806d8b42f938")
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 module. 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 os
import sys
import tempfile
import importlib.util

# Create a temporary directory structure for testing
temp_dir = tempfile.mkdtemp()
classification_dir = os.path.join(temp_dir, 'classification')
os.makedirs(classification_dir, exist_ok=True)

# Create a simple models.py module in the classification directory
models_file = os.path.join(classification_dir, 'models.py')
with open(models_file, 'w') as f:
    f.write("""
# Dummy models module
class DummyModel:
    pass

def dummy_function():
    return "models module loaded"
""")

# Create __init__.py to make it a package
init_file = os.path.join(classification_dir, '__init__.py')
with open(init_file, 'w') as f:
    f.write("")

ARGS = {
    'name': 'models',
    'path': classification_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 module — a module output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a module 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
selective_scan_torch Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
VISION-SJTU/PVMamba/classification/models/utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from chenxi52/SfMamba, is pointer only (licence: NONE) · get_code("82e4cdd256f30ead")
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 chenxi52/SfMamba, 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.

set_weight_decay Ran
ran; our contract draft was wrong, not the code
VISION-SJTU/PVMamba/classification/utils/optimizer.py
code served (permissive licence) · get_code("2d5473f673967c35")
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

torch.manual_seed(0)

# Create a small model for testing
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        # Add parameters with different shapes
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
        self.bn = nn.BatchNorm1d(3)
        self.embedding = nn.Embedding(5, 4)
    
    def forward(self, x):
        return x

model = SimpleModel()

# Create skip_list with a parameter name that exists in the model
skip_list = ('embedding.weight',)

# Create skip_keywords with common keywords to skip (e.g., 'bias', 'norm')
skip_keywords = ('norm',)

ARGS = {
    'model': model,
    'skip_list': skip_list,
    'skip_keywords': skip_keywords,
}
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
spatial_adaptive_sampling_core_pytorch Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
VISION-SJTU/PVMamba/classification/models/pvmamba.py
code served (permissive licence) · get_code("2fc7260a29b07cc9")
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 4, dtype family float, shape (6, 4, 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.functional as F

torch.manual_seed(0)

# Parameters:
# - value: shape (N_, S_, M_, D_) where N_=batch, S_=spatial_sum, M_=num_heads, D_=feature_dim
# - value_spatial_shapes: list of (H_, W_) tuples for each level
# - sampling_locations: shape (N_, Lq_, M_, L_, P_, 2) where Lq_=query_len, L_=num_levels, P_=num_points

N_ = 2  # batch size
M_ = 3  # number of heads/groups
D_ = 4  # feature dimension
Lq_ = 5  # query length
L_ = 2  # number of levels
P_ = 4  # number of sampling points per query per level

# Define spatial shapes for 2 levels
H_0, W_0 = 8, 6
H_1, W_1 = 4, 3
value_spatial_shapes = [(H_0, W_0), (H_1, W_1)]

# Total spatial dimension: sum of H*W for all levels
S_ = H_0 * W_0 + H_1 * W_1  # 48 + 12 = 60

# value: (N_, S_, M_, D_) = (2, 60, 3, 4)
value = torch.randn(N_, S_, M_, D_)

# sampling_locations: (N_, Lq_, M_, L_, P_, 2) = (2, 5, 3, 2, 4, 2)
# Each sampling location is normalized to [0, 1] range (will be converted to [-1, 1])
sampling_locations = torch.rand(N_, Lq_, M_, L_, P_, 2)

ARGS = {
    "value": value,
    "value_spatial_shapes": value_spatial_shapes,
    "sampling_locations": sampling_locations,
}
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 4, dtype family float, shape (6, 4, 5, 4) — shape (6, 4, 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
get_config Not yet run
unverified (harvested, no recorded run)
VISION-SJTU/PVMamba/classification/config.py
code served (permissive licence) · get_code("3760f0a84c81308d")
How it ran

no invocation recorded.

load_checkpoint_ema Not yet run
unverified (harvested, no recorded run)
VISION-SJTU/PVMamba/classification/utils/utils.py
code served (permissive licence) · get_code("c3565ec7e9c7f4df")
How it ran

no invocation recorded.

update_config Not yet run
unverified (harvested, no recorded run)
VISION-SJTU/PVMamba/classification/config.py
code served (permissive licence) · get_code("13920ae73055d5cf")
How it ran

no invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 14 are also present in other papers whose code we hold (13 with at least one paper dated earlier, 0 the same month, 4 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
get_config 51 other papers
47 dated earlier, 1 later, 3 same year, order not determinable
2103.14030 (2021-03)
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
2106.03650 (2021-06)
Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer
2106.03746 (2021-06)
Efficient Training of Visual Transformers with Small Datasets
and 48 more not named here
create_logger 35 other papers
33 dated earlier, 2 same year, order not determinable
2104.13840 (2021-04)
Twins: Revisiting the Design of Spatial Attention in Vision Transformers
2106.03650 (2021-06)
Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer
2106.03746 (2021-06)
Efficient Training of Visual Transformers with Small Datasets
and 32 more not named here
check_keywords_in_name 31 other papers
29 dated earlier, 2 same year, order not determinable
2103.14030 (2021-03)
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
2106.03650 (2021-06)
Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer
2106.03746 (2021-06)
Efficient Training of Visual Transformers with Small Datasets
and 28 more not named here
get_grad_norm 23 other papers
21 dated earlier, 2 same year, order not determinable
1910.13616 (2019-10)
Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation
2103.14030 (2021-03)
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
2106.03650 (2021-06)
Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer
and 20 more not named here
flops_selective_scan_fn 12 other papers
8 dated earlier, 2 later, 2 same year, order not determinable
2401.10166 (2024-01)
VMamba: Visual State Space Model
2402.15648 (2024-02)
MambaIR: A Simple Baseline for Image Restoration with State-Space Model
2403.17839 (2024-03)
ReMamber: Referring Image Segmentation with Mamba Twister
and 9 more not named here
flops_selective_scan_ref 9 other papers
8 dated earlier, 1 later
2401.10166 (2024-01)
VMamba: Visual State Space Model
2402.15648 (2024-02)
MambaIR: A Simple Baseline for Image Restoration with State-Space Model
2403.09977 (2024-03)
EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba
and 6 more not named here
build_scheduler 3 other papers
3 dated earlier
2407.10240 (2024-07)
xLSTMTime : Long-term Time Series Forecasting With xLSTM
2407.19394 (2024-07)
Depth-Wise Convolutions in Vision Transformers for Efficient Training on Small Datasets
2410.15091 (2024-10)
Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State Fusion
import_abspy 3 other papers
3 dated earlier
2403.09977 (2024-03)
EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba
2407.18559 (2024-07)
VSSD: Vision Mamba with Non-Causal State Space Duality
2410.15091 (2024-10)
Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State Fusion
selective_scan_torch 2 other papers
2 later
2601.06891 (2026-01)
Contrastive Language-Image Mamba Pretraining
2601.08608 (2026-01)
SfMamba: Efficient Source-Free Domain Adaptation via Selective Scan Modeling
set_weight_decay 2 other papers
2 dated earlier
2404.07794 (2024-04)
DGMamba: Domain Generalization via Generalized State Space Model
2410.15091 (2024-10)
Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State Fusion
auto_resume_helper 1 other paper
1 dated earlier
2410.15091 (2024-10)
Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State Fusion
build_optimizer 1 other paper
1 dated earlier
2410.15091 (2024-10)
Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State Fusion
load_checkpoint_ema 1 other paper
1 dated earlier
2410.15091 (2024-10)
Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State Fusion
update_config 1 other paper
1 dated earlier
2410.15091 (2024-10)
Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State Fusion

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

Mamba, an architecture with RNN-like sequence modeling of State Space Model (SSM), has demonstrated promising capabilities in long-range modeling with high efficiency. However, Mamba models struggle with structured 2D visual data using sequential computing, thereby lagging behind their attention-based counterparts. In this paper, we propose a Parallel Vision Mamba (PVMamba), a novel SSM architecture tailored for visual data. PVMamba encompasses two key designs: 1) Based on the sparsity and adjacency of visual signals, we parallelize the sequential computing through three core steps, termed Dynamic State Aggregation (DSA), i.e., parallelization, alignment, and aggregation. DSA generates the hidden state in SSM by a feasible spatial aggregation, thereby overcoming the inherent sequential constraints. 2) Along with maintaining linear computational complexity, we apply a dynamic operator to learn the spatial samplings for each hidden state. To further boost the local modeling capability, we restrict the dynamic operator to the neighboring pixels in shallow layers. We also devise a layer multiplexing technique to stabilize the training and reduce the learning redundancy. PVMamba is a versatile backbone network with dynamic operators for various vision tasks, such as image classification and dense prediction. Extensive experiments show that PVMamba achieves state-of-the-art performance on a range of benchmarks. The code is available at https: //github.com/VISION-SJTU/PVMamba.

For agents

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

get_harvested_code_for_paper("Xie_PVMamba_Parallelizing_Vision_Mamba_via_Dynamic_State_Aggregation_ICCV_2025_paper")
get_code_for_paper("Xie_PVMamba_Parallelizing_Vision_Mamba_via_Dynamic_State_Aggregation_ICCV_2025_paper")
have("Xie_PVMamba_Parallelizing_Vision_Mamba_via_Dynamic_State_Aggregation_ICCV_2025_paper")

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

curl https://syntology.ai/api/ran/Xie_PVMamba_Parallelizing_Vision_Mamba_via_Dynamic_State_Aggregation_ICCV_2025_paper.json

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

[![Syntology run record](https://syntology.ai/api/ran/Xie_PVMamba_Parallelizing_Vision_Mamba_via_Dynamic_State_Aggregation_ICCV_2025_paper.svg)](https://syntology.ai/paper/Xie_PVMamba_Parallelizing_Vision_Mamba_via_Dynamic_State_Aggregation_ICCV_2025_paper)

Connect an agent — have() is free.