SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.09059 · 2023

Auto-Prox: Training-Free Vision Transformer Architecture Search via Automatic Proxy Discovery

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 0 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/2312.09059.json · badge: /api/ran/2312.09059.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
lilujunai/auto-prox-aaai24 canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
FunctionStatusWhere it lives
calc_dropout Ran
ran, honoured the contract we drafted
lilujunai/auto-prox-aaai24/pycls/models/auto/autoformer_supernet.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from liangyn22/mcuformer, is pointer only (licence: NONE) · get_code("72a860a9aff50105")
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 liangyn22/mcuformer, 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.

gelu Ran
ran, honoured the contract we drafted
lilujunai/auto-prox-aaai24/pycls/models/auto/autoformer_subnet.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from liangyn22/mcuformer, is pointer only (licence: NONE) · get_code("08a5be1ffa0676e3")
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 liangyn22/mcuformer, 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_bias Ran
ran; our contract draft was wrong, not the code
lilujunai/auto-prox-aaai24/pycls/models/auto/module/Linear_super.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from liangyn22/mcuformer, is pointer only (licence: NONE) · get_code("963bc33b77cf8148")
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 liangyn22/mcuformer, 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_weight Ran
ran; our contract draft was wrong, not the code
lilujunai/auto-prox-aaai24/pycls/models/auto/module/Linear_super.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from liangyn22/mcuformer, is pointer only (licence: NONE) · get_code("1d3488a4b38ea75d")
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 liangyn22/mcuformer, 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.

softmax Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
lilujunai/auto-prox-aaai24/pycls/models/auto/module/multihead_super.py
code served (permissive licence) · get_code("fb5908c47c2af90c")
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
import torch.nn.functional as F

torch.manual_seed(0)

# Create a small tensor with shape (2, 4)
x = torch.randn(2, 4)

# dim parameter - which dimension to apply softmax over
dim = 1

# onnx_trace parameter - boolean flag
onnx_trace = False

ARGS = {
    "x": x,
    "dim": dim,
    "onnx_trace": onnx_trace
}
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

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 5 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 5 later) and 0 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
calc_dropout 4 other papers
3 dated earlier, 1 later · 1 only as an assembly brick
2206.04673 (2022-06)
Neural Prompt Search
2304.14636 (2023-04)
PreNAS: Preferred One-Shot Learning Towards Efficient Neural Architecture Search
2310.16898 (2023-10)
MCUFormer: Deploying Vision Transformers on Microcontrollers with Limited Memory
and 1 more not named here
gelu 4 other papers
3 dated earlier, 1 later · 1 only as an assembly brick
2206.04673 (2022-06)
Neural Prompt Search
2304.14636 (2023-04)
PreNAS: Preferred One-Shot Learning Towards Efficient Neural Architecture Search
2310.16898 (2023-10)
MCUFormer: Deploying Vision Transformers on Microcontrollers with Limited Memory
and 1 more not named here
sample_bias 4 other papers
3 dated earlier, 1 later · 2 only as an assembly brick
2106.09685 (2021-06)
LoRA: Low-Rank Adaptation of Large Language Models
2304.14636 (2023-04)
PreNAS: Preferred One-Shot Learning Towards Efficient Neural Architecture Search
2310.16898 (2023-10)
MCUFormer: Deploying Vision Transformers on Microcontrollers with Limited Memory
and 1 more not named here
sample_weight 4 other papers
3 dated earlier, 1 later · 2 only as an assembly brick
2106.09685 (2021-06)
LoRA: Low-Rank Adaptation of Large Language Models
2304.14636 (2023-04)
PreNAS: Preferred One-Shot Learning Towards Efficient Neural Architecture Search
2310.16898 (2023-10)
MCUFormer: Deploying Vision Transformers on Microcontrollers with Limited Memory
and 1 more not named here
softmax 1 other paper
1 later
aaai_29511 (2024 (year only))
Auto-Prox: Training-Free Vision Transformer Architecture Search via Automatic Proxy Discovery

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

The substantial success of Vision Transformer (ViT) in computer vision tasks is largely attributed to the architecture design. This underscores the necessity of efficient architecture search for designing better ViTs automatically. As training-based architecture search methods are computationally intensive, there is a growing interest in training-free methods that use zero-cost proxies to score ViTs. However, existing training-free approaches require expert knowledge to manually design specific zero-cost proxies. Moreover, these zero-cost proxies exhibit limitations to generalize across diverse domains. In this paper, we introduce Auto-Prox, an automatic proxy discovery framework, to address the problem. First, we build the ViT-Bench-101, which involves different ViT candidates and their actual performance on multiple datasets. Utilizing ViT-Bench-101, we can evaluate zero-cost proxies based on their score-accuracy correlation. Then, we represent zero-cost proxies with computation graphs and organize the zero-cost proxy search space with ViT statistics and primitive operations. To discover generic zero-cost proxies, we propose a joint correlation metric to evolve and mutate different zero-cost proxy candidates. We introduce an elitism-preserve strategy for search efficiency to achieve a better trade-off between exploitation and exploration. Based on the discovered zero-cost proxy, we conduct a ViT architecture search in a training-free manner. Extensive experiments demonstrate that our method generalizes well to different datasets and achieves state-of-the-art results both in ranking correlation and final accuracy. Codes can be found at https://github.com/lilujunai/Auto-Prox-AAAI24.

For agents

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

get_harvested_code_for_paper("2312.09059")
get_code_for_paper("2312.09059")
have("2312.09059")

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

curl https://syntology.ai/api/ran/2312.09059.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.09059.svg)](https://syntology.ai/paper/2312.09059)

Connect an agent — have() is free.