SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.09417 · ICML · 2024

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

Qian Zhang, Wenyu Liu, Xinggang Wang, Xinlong Wang, Bencheng Liao, Lianghui Zhu

arXiv · PDF · Open in the Atlas

Code that ran

8 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; 1 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 2 failures of our instrument; 5 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/2401.09417.json · badge: /api/ran/2401.09417.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
younghyun197/ptq4vm community (classifier label)
classifier basis not recorded on the link
7 ran · 5 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
ampscaler_get_grad_norm Ran
ran, honoured the contract we drafted
younghyun197/ptq4vm/ptq4vm/utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Aaronhuang-778/SliM-LLM, is pointer only (licence: NONE) · get_code("c07dba9529e937b7")
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 Aaronhuang-778/SliM-LLM, 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
younghyun197/ptq4vm/ptq4vm/utils.py
code served (permissive licence) · get_code("971871ec92e49a7c")
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 os
import tempfile
import logging

# Create a temporary directory for output
temp_dir = tempfile.mkdtemp()

ARGS = {
    'output_dir': temp_dir,
    'dist_rank': 0,
    'name': 'test_logger'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
termcolor — 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
get_act_scales Ran
ran on a synthesized input
younghyun197/ptq4vm/generate_act_scale.py
code served (permissive licence) · get_code("bce8067973682f24")
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. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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)

# Build a small model with Linear layers
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model = SimpleModel()

# Build a small dataloader as a list of (input, label) tuples
# Batch size 2, input dim 4
dataloader = [
    (torch.randn(2, 4), torch.randint(0, 2, (2,))),
    (torch.randn(2, 4), torch.randint(0, 2, (2,))),
]

ARGS = {
    "model": model,
    "dataloader": dataloader,
}
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 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_parameters_all Ran
ran on a synthesized input
younghyun197/ptq4vm/ptq4vm/jlss.py
code served (permissive licence) · get_code("d1ee14347d11a9d6")
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 list_iterator. 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)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.layer1 = nn.Linear(4, 3)
        self.s = nn.Parameter(torch.randn(2))
        self.layer2 = nn.Linear(3, 2)
        self.smooth_scale = nn.Parameter(torch.randn(5))
        self.other_param = nn.Parameter(torch.randn(3))
    
    def forward(self, x):
        return self.layer2(self.layer1(x))

model = SimpleModel()

ARGS = {
    "model": model
}
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 list_iterator — a list_iterator output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a list_iterator 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_quant_parameters Ran
ran on a synthesized input
younghyun197/ptq4vm/ptq4vm/jlss.py
code served (permissive licence) · get_code("b1e4ada8a9c5fac0")
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, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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)

class QuantModule(nn.Module):
    def __init__(self):
        super().__init__()
        # Create parameters that match the naming patterns the function looks for
        self.proj = nn.Module()
        self.proj.s = nn.Parameter(torch.randn(4, 3), requires_grad=True)
        
        self.act_func = nn.Module()
        self.act_func.s = nn.Parameter(torch.randn(2, 5), requires_grad=True)
        
        # Add some other parameters to ensure the function filters correctly
        self.weight = nn.Parameter(torch.randn(3, 4), requires_grad=True)
        self.bias = nn.Parameter(torch.randn(2), requires_grad=True)

class Model(nn.Module):
    def __init__(self):
        super().__init__()
        self.layer1 = QuantModule()
        self.layer2 = QuantModule()
    
    def forward(self, x):
        return x

model = Model()

ARGS = {
    "model": model
}
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, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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_quant_parameters Ran
ran on a synthesized input
younghyun197/ptq4vm/VMamba/classification/ptq4vm/jlss.py
code served (permissive licence) · get_code("b7abefcac9f98958")
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, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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)

class QuantLayer(nn.Module):
    def __init__(self):
        super().__init__()
        self.s = nn.Parameter(torch.tensor(1.0), requires_grad=True)
    
    def forward(self, x):
        return x * self.s

class ActFunc(nn.Module):
    def __init__(self):
        super().__init__()
        self.s = nn.Parameter(torch.tensor(0.5), requires_grad=True)
    
    def forward(self, x):
        return torch.relu(x * self.s)

class QuantModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.layer1_s = nn.Parameter(torch.tensor(2.0), requires_grad=True)
        self.layer2 = QuantLayer()
        self.act_func = ActFunc()
        self.other_param = nn.Parameter(torch.tensor(1.5), requires_grad=True)
    
    def forward(self, x):
        x = x * self.layer1_s
        x = self.layer2(x)
        x = self.act_func(x)
        return x

model = QuantModel()

ARGS = {
    'model': model
}
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, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
int_quantizer_BWD Ran
ran on a synthesized input
younghyun197/ptq4vm/cuda_measure/cuda_sandbox.py
code served (permissive licence) · get_code("ce2c1c8e2c3f9e18")
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 (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 a small tensor to quantize
# The function uses: x.abs().max(), torch.clamp(), torch.round()
# So we need a real tensor with mixed positive/negative values
x = torch.randn(2, 4)

ARGS = {
    "x": x,
    "quantBits": 4
}
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 (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
rand_bbox Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from psandovalsegura/learn-from-unlearnable
pointer only; the stored copy get_code serves, from psandovalsegura/learn-from-unlearnable, is pointer only (licence: NONE) · get_code("0756a99508caf42c")
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.

get_acc_convnext Not yet run
unverified (harvested, no recorded run)
younghyun197/ptq4vm/VMamba/analyze/loss.py
code served (permissive licence) · get_code("557ec75e2d4f69a3")
How it ran

no invocation recorded.

get_acc_swin Not yet run
unverified (harvested, no recorded run)
younghyun197/ptq4vm/VMamba/analyze/loss.py
code served (permissive licence) · get_code("56be5106b964214d")
How it ran

no invocation recorded.

get_loss_convnext Not yet run
unverified (harvested, no recorded run)
younghyun197/ptq4vm/VMamba/analyze/loss.py
code served (permissive licence) · get_code("0ab36f06185946ed")
How it ran

no invocation recorded.

get_smooth_parameters Not yet run
unverified (harvested, no recorded run)
younghyun197/ptq4vm/ptq4vm/jlss.py
code served (permissive licence) · get_code("3d2f55555ee9cf38")
How it ran

no invocation recorded.

get_smooth_parameters Not yet run
unverified (harvested, no recorded run)
younghyun197/ptq4vm/VMamba/classification/ptq4vm/jlss.py
code served (permissive licence) · get_code("2843c9584217797b")
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 13 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 later) and 10 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
rand_bbox 8 other papers
3 dated earlier, 5 later
2112.00412 (2021-12)
The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification
2305.19254 (2023-05)
What Can We Learn from Unlearnable Datasets?
2312.08939 (2023-12)
EAT: Towards Long-Tailed Out-of-Distribution Detection
and 5 more not named here
create_logger 7 other papers
1 dated earlier, 6 later
2308.13137 (2023-08)
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
2403.12544 (2024-03)
AffineQuant: Affine Transformation Quantization for Large Language Models
2405.14917 (2024-05)
SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models
and 4 more not named here
ampscaler_get_grad_norm 3 other papers
1 dated earlier, 2 later
2308.13137 (2023-08)
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
2405.14917 (2024-05)
SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models
2506.03781 (2025-06)
Unifying Uniform and Binary-coding Quantization for Accurate Compression of Large Language Models

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

and our Vim model. Results show that Vim outperforms DeiT on both ImageNet classification and downstream detection and segmentation tasks and is more computation and memory efficient than DeiT in dealing with high-resolution images. For example, Vim is 2.8× faster than DeiT and saves 86.8% GPU memory when performing batch inference to extract features on images with a resolution of 1248×1248, i.e., 6084 tokens per image.

For agents

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

get_harvested_code_for_paper("2401.09417")
get_code_for_paper("2401.09417")
have("2401.09417")

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

curl https://syntology.ai/api/ran/2401.09417.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.09417.svg)](https://syntology.ai/paper/2401.09417)

Connect an agent — have() is free.