SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2501.15369 · ICLR · 2025

iFormer: Integrating ConvNet and Transformer for Mobile Application

Chuanyang Zheng

arXiv · PDF · Open in the Atlas

Code that ran

5 of 10 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (4 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 1 failure 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/2501.15369.json · badge: /api/ran/2501.15369.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
ChuanyangZheng/iFormer canonical (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
chuanyangzheng/iformer community
Papers with Code archive
4 ran · 2 no recorded run
sail-sg/iFormer reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
0 ran · 1 no recorded run
FunctionStatusWhere it lives
BN_Linear Ran
ran on a synthesized input · constructed an object; no result was computed
chuanyangzheng/iformer/models/iformer.py
code served (permissive licence) · get_code("00bd980cb0c92bbc")
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, BN_Linear: 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 timm.models.layers import trunc_normal_, DropPath

torch.manual_seed(0)

# The BN_Linear class takes parameters:
# - a: input dimension
# - b: output dimension
# - bias: boolean (default True)
# - std: float (default 0.02)

# Looking at the __init__ method:
# - Creates BatchNorm1d(a) - needs a to be an int
# - Creates Linear(a, b, bias=bias) - needs a, b to be ints
# - Uses trunc_normal_ on weight with std parameter
# - Initializes bias to 0 if it exists

# Looking at the fuse method:
# - Accesses bn, l from self._modules.values()
# - Uses bn.weight, bn.running_var, bn.eps, bn.bias, bn.running_mean
# - Uses l.weight, l.bias
# - Creates a new Linear layer with proper dimensions
# All of these are standard BatchNorm1d and Linear attributes

# Set up small, distinct dimensions
a = 4  # input dimension
b = 3  # output dimension
bias = True
std = 0.02

ARGS = {
    'a': a,
    'b': b,
    'bias': bias,
    'std': std
}
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 BN_Linear — 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 BN_Linear output the recorded ndim 1 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
Classfier Ran
ran on a synthesized input · constructed an object; no result was computed
chuanyangzheng/iformer/models/iformer.py
code served (permissive licence) · get_code("be930a9ccda0b4c9")
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, Classfier: 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)

ARGS = {
    'dim': 4,
    'num_classes': 3,
    'distillation': False
}
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 Classfier — 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 Classfier 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
Conv2d_BN Ran
ran on a synthesized input · constructed an object; no result was computed
chuanyangzheng/iformer/models/iformer.py
code served (permissive licence) · get_code("1adb071078d6909f")
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, Conv2d_BN: 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)

ARGS = {
    'a': 3,
    'b': 16,
    'ks': 3,
    'stride': 1,
    'pad': 1,
    'dilation': 1,
    'groups': 1,
    'bn_weight_init': 1,
    'resolution': -10000
}
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 Conv2d_BN — 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 Conv2d_BN output the recorded ndim 1 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
EdgeResidual Ran
ran on a synthesized input · constructed an object; no result was computed
chuanyangzheng/iformer/models/iformer.py
code served (permissive licence) · get_code("fc32f0783a025e82")
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, EdgeResidual: 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)

ARGS = {
    'in_chs': 16,
    'out_chs': 32,
    'exp_kernel_size': 3,
    'stride': 1,
    'exp_ratio': 1.0,
    'act_layer': nn.ReLU,
}
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 EdgeResidual — 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 EdgeResidual 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
window_partition Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ChuanyangZheng/iFormer/detection/iformer.py
code served (permissive licence) · get_code("7a3f740ecc375589")
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 4, dtype family float, shape (8, 4, 4, 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 with shape (B, C, H, W)
# B=2 (batch), C=4 (channels), H=8 (height), W=8 (width)
# These dimensions are chosen so they're divisible by window_size
x = torch.randn(2, 4, 8, 8)

# Window size
window_size = 4

ARGS = {
    "x": x,
    "window_size": window_size,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (8, 4, 4, 4) — shape (8, 4, 4, 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
BasicBlock Not yet run
unverified (harvested, no recorded run)
chuanyangzheng/iformer/models/iformer.py
code served (permissive licence) · get_code("ffef9979cc983271")
How it ran

no invocation recorded.

concat_all_gather Not yet run
unverified (harvested, no recorded run)
sail-sg/iFormer/fine-tune.py
code served (permissive licence) · get_code("73cecca9f3575f09")
How it ran

no invocation recorded.

iFormer Not yet run
unverified (harvested, no recorded run)
chuanyangzheng/iformer/models/iformer.py
code served (permissive licence) · get_code("5931f19101efb167")
How it ran

no invocation recorded.

validate Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from elicassion/3DTRL
pointer only · get_code("e2a98c6a53ded11f")
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. No invocation recorded.

window_reverse Not yet run
unverified (harvested, no recorded run)
ChuanyangZheng/iFormer/detection/iformer.py
code served (permissive licence) · get_code("7f2b1f05bf53f1b7")
How it ran

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, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 1 later) and 8 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
concat_all_gather 138 other papers
125 dated earlier, 1 the same month, 9 later, 3 same year, order not determinable · 33 only as an assembly brick
1710.09412 (2017-10)
mixup: BEYOND EMPIRICAL RISK MINIMIZATION
1905.04899 (2019-05)
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
and 135 more not named here
validate 9 other papers
9 dated earlier
2103.15632 (2021-03)
Regular Polytope Networks
2107.00652 (2021-07)
CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows
2204.05173 (2022-04)
Machine Learning State-of-the-Art with Uncertainties
and 6 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

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

Abstract

We present a new family of mobile hybrid vision networks, called iFormer, with a focus on optimizing latency and accuracy on mobile applications. iFormer effectively integrates the fast local representation capacity of convolution with the efficient global modeling ability of self-attention. The local interactions are derived from transforming a standard convolutional network, i.e., ConvNeXt, to design a more lightweight mobile network. Our newly introduced mobile modulation attention removes memory-intensive operations in MHA and employs an efficient modulation mechanism to boost dynamic global representational capacity. We conduct comprehensive experiments demonstrating that iFormer outperforms existing lightweight networks across various tasks. Notably, iFormer achieves an impressive Top-1 accuracy of 80.4% on ImageNet-1k with a latency of only 1.10 ms on an iPhone 13, surpassing the recently proposed MobileNetV4 under similar latency constraints. Additionally, our method shows significant improvements in downstream tasks, including COCO object detection, instance segmentation, and ADE20k semantic segmentation, while still maintaining low latency on mobile devices for high-resolution inputs in these scenarios. Code and models are available at: https://github.com/ChuanyangZheng/iFormer.

For agents

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

get_harvested_code_for_paper("2501.15369")
get_code_for_paper("2501.15369")
have("2501.15369")

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

curl https://syntology.ai/api/ran/2501.15369.json

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

[![Syntology run record](https://syntology.ai/api/ran/2501.15369.svg)](https://syntology.ai/paper/2501.15369)

Connect an agent — have() is free.