SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.02068 · 2024

LPViT: Low-Power Semi-structured Pruning for Vision Transformers

arXiv · PDF · Open in the Atlas

Code that ran

12 of 12 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; 4 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 7 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/2407.02068.json · badge: /api/ran/2407.02068.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
Akimoto-Cris/LPViT canonical (classifier label)
classifier basis: census
12 ran · 0 no recorded run
FunctionStatusWhere it lives
blocksparse_attention_mask Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Akimoto-Cris/LPViT/blocksparse_attention_module.py
pointer only (licence: NONE) · get_code("1f571409b5239217")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Akimoto-Cris/LPViT 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.

check_sparsity Ran
ran, honoured the contract we drafted
Akimoto-Cris/LPViT/pruning_utils.py
pointer only (licence: NONE) · get_code("de2af715a05df3be")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Akimoto-Cris/LPViT 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.

check_sparsity_dict Ran
ran, honoured the contract we drafted
Akimoto-Cris/LPViT/pruning_utils.py
pointer only (licence: NONE) · get_code("181028f4d3a799d6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Akimoto-Cris/LPViT 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.

extract_mask Ran
ran; our contract draft was wrong, not the code
Akimoto-Cris/LPViT/pruning_utils.py
pointer only (licence: NONE) · get_code("cccbdd267d4f7850")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Akimoto-Cris/LPViT 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.

get_sparsity Ran
ran, honoured the contract we drafted
Akimoto-Cris/LPViT/engine.py
pointer only (licence: NONE) · get_code("9f7f6915bde67e3d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Akimoto-Cris/LPViT 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.

get_spraseattention_vit_module Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Akimoto-Cris/LPViT/blocksparse_attention_module.py
pointer only (licence: NONE) · get_code("73d3cb525b1c3172")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Akimoto-Cris/LPViT 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.

get_tau Ran
ran, violated the contract we drafted
Akimoto-Cris/LPViT/engine.py
pointer only (licence: NONE) · get_code("aa9253d77220768c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Akimoto-Cris/LPViT 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.

gumbel_softmax Ran
ran; our contract draft was wrong, not the code
Akimoto-Cris/LPViT/sp_vision_transformer.py
pointer only (licence: NONE) · get_code("7c73b690d9886b5d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Akimoto-Cris/LPViT 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.

resize_pos_embed Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Akimoto-Cris/LPViT/sp_vision_transformer.py
pointer only (licence: NONE) · get_code("743923947c250e6c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Akimoto-Cris/LPViT 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.

scatter Ran
ran; our contract draft was wrong, not the code
Akimoto-Cris/LPViT/sp_vision_transformer.py
pointer only (licence: NONE) · get_code("e11ddb5cae4f73b4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Akimoto-Cris/LPViT 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.

sparse_attention_mask Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Akimoto-Cris/LPViT/blocksparse_attention_module.py
pointer only (licence: NONE) · get_code("09f6b361c824b0d7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Akimoto-Cris/LPViT 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.

test Ran
ran, honoured the contract we drafted
Akimoto-Cris/LPViT/prune_vit.py
pointer only (licence: NONE) · get_code("49e75bdeacd88ac2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Akimoto-Cris/LPViT 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.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 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, 0 later) and 9 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
extract_mask 2 other papers
2 dated earlier
2106.03225 (2021-06)
Efficient Lottery Ticket Finding: Less Data is More
2206.04762 (2022-06)
Data-Efficient Double-Win Lottery Tickets from Robust Pre-training
get_tau 1 other paper
1 dated earlier
2203.08243 (2022-03)
Unified Visual Transformer Compression
resize_pos_embed 1 other paper
1 dated earlier
2203.06345 (2022-03)
The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy

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

Vision transformers have emerged as a promising alternative to convolutional neural networks for various image analysis tasks, offering comparable or superior performance. However, one significant drawback of ViTs is their resource-intensive nature, leading to increased memory footprint, computation complexity, and power consumption. To democratize this high-performance technology and make it more environmentally friendly, it is essential to compress ViT models, reducing their resource requirements while maintaining high performance. In this paper, we introduce a new block-structured pruning to address the resource-intensive issue for ViTs, offering a balanced trade-off between accuracy and hardware acceleration. Unlike unstructured pruning or channel-wise structured pruning, block pruning leverages the block-wise structure of linear layers, resulting in more efficient matrix multiplications. To optimize this pruning scheme, our paper proposes a novel hardware-aware learning objective that simultaneously maximizes speedup and minimizes power consumption during inference, tailored to the block sparsity structure. This objective eliminates the need for empirical look-up tables and focuses solely on reducing parametrized layer connections. Moreover, our paper provides a lightweight algorithm to achieve post-training pruning for ViTs, utilizing second-order Taylor approximation and empirical optimization to solve the proposed hardware-aware objective. Extensive experiments on ImageNet are conducted across various ViT architectures, including DeiT-B and DeiT-S, demonstrating competitive performance with other pruning methods and achieving a remarkable balance between accuracy preservation and power savings. Especially, we achieve 3.93x speedup on dedicated hardware and GPUs respectively for DeiT-B, and a power reduction by 1.4x on GPUs. Code released to https://github.com/Akimoto-Cris/LPViT.

For agents

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

get_harvested_code_for_paper("2407.02068")
get_code_for_paper("2407.02068")
have("2407.02068")

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

curl https://syntology.ai/api/ran/2407.02068.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.02068.svg)](https://syntology.ai/paper/2407.02068)

Connect an agent — have() is free.