SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2501.06884 · NeurIPS · 2025

Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learning

Di Huang, Jiaxin Chen, Yunhong Wang, Yutong Zhang, Hanwen Zhong

arXiv · PDF · Open in the Atlas

Code that ran

3 of 7 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 0 have no contract verdict; 2 failures of our instrument; 4 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/2501.06884.json · badge: /api/ran/2501.06884.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
yewen1486/emtal canonical (classifier label)
classifier basis: classifier_2025
3 ran · 4 no recorded run
FunctionStatusWhere it lives
init_ssf_scale_shift Ran
ran; our contract draft was wrong, not the code
yewen1486/emtal/models/vision_transformer.py
pointer only (licence: NONE) · get_code("896b5eec245f1bab")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yewen1486/emtal 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.

param_groups_weight_decay Ran
ran; our contract draft was wrong, not the code
yewen1486/emtal/optim_factory.py
pointer only (licence: NONE) · get_code("88f4962784e09b88")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yewen1486/emtal 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.

ssf_ada Ran
ran, honoured the contract we drafted
yewen1486/emtal/models/vision_transformer.py
pointer only (licence: NONE) · get_code("61e8364b7e9bcb70")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yewen1486/emtal 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.

group_parameters Not yet run
unverified (harvested, no recorded run)
yewen1486/emtal/optim_factory.py
pointer only (licence: NONE) · get_code("efeb37d90ba28266")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yewen1486/emtal 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. No invocation recorded.

group_with_matcher Not yet run
unverified (harvested, no recorded run)
yewen1486/emtal/optim_factory.py
pointer only (licence: NONE) · get_code("0332519996466b5a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yewen1486/emtal 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. No invocation recorded.

kl_divergence_loss Not yet run
unverified (harvested, no recorded run)
yewen1486/emtal/train_EMTAL.py
pointer only (licence: NONE) · get_code("3fdc6c4f02598de3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yewen1486/emtal 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. No invocation recorded.

validate Not yet run
unverified (harvested, no recorded run)
yewen1486/emtal/train_EMTAL.py
pointer only (licence: NONE) · get_code("e2ee008f3497204c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yewen1486/emtal 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. No invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 2 later) and 2 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
param_groups_weight_decay 15 other papers
13 dated earlier, 2 later
2210.08823 (2022-10)
Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning
2304.14065 (2023-04)
Lightweight, Pre-trained Transformers for Remote Sensing Timeseries
2305.13002 (2023-05)
Rethinking Semi-supervised Learning with Language Models
and 12 more not named here
ssf_ada 8 other papers
8 dated earlier · 1 only as an assembly brick
2210.08823 (2022-10)
Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning
2307.02251 (2023-07)
RanPAC: Random Projections and Pre-trained Models for Continual Learning
2307.11342 (2023-07)
Tuning Pre-trained Model via Moment Probing
and 5 more not named here
init_ssf_scale_shift 7 other papers
7 dated earlier
2210.08823 (2022-10)
Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning
2307.02251 (2023-07)
RanPAC: Random Projections and Pre-trained Models for Continual Learning
2307.11342 (2023-07)
Tuning Pre-trained Model via Moment Probing
and 4 more not named here
group_parameters 6 other papers
5 dated earlier, 1 later
2210.08823 (2022-10)
Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning
2307.11342 (2023-07)
Tuning Pre-trained Model via Moment Probing
2308.13168 (2023-08)
IOMatch: Simplifying Open-Set Semi-Supervised Learning with Joint Inliers and Outliers Utilization
and 3 more not named here
group_with_matcher 4 other papers
4 dated earlier
2210.08823 (2022-10)
Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning
2307.11342 (2023-07)
Tuning Pre-trained Model via Moment Probing
2312.10136 (2023-12)
Gradient-based Parameter Selection for Efficient Fine-Tuning
and 1 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

Multi-Task Learning (MTL) for Vision Transformer aims at enhancing the model capability by tackling multiple tasks simultaneously. Most recent works have predominantly focused on designing Mixture-of-Experts (MoE) structures and integrating Low-Rank Adaptation (LoRA) to efficiently perform multi-task learning. However, their rigid combination hampers both the optimization of MoE and the effectiveness of reparameterization of LoRA, leading to sub-optimal performance and low inference speed. In this work, we propose a novel approach dubbed Efficient Multi-Task Learning (EMTAL) by transforming a pre-trained Vision Transformer into an efficient multi-task learner during training, and reparameterizing the learned structure for efficient inference. Specifically, we firstly develop the MoEfied LoRA structure, which decomposes the pre-trained Transformer into a low-rank MoE structure and employ LoRA to fine-tune the parameters. Subsequently, we take into account the intrinsic asynchronous nature of multi-task learning and devise a learning Quality Retaining (QR) optimization mechanism, by leveraging the historical high-quality class logits to prevent a well-trained task from performance degradation. Finally, we design a router fading strategy to integrate the learned parameters into the original Transformer, archiving efficient inference. Extensive experiments on public benchmarks demonstrate the superiority of our method, compared to the state-of-the-art multi-task learning approaches. The project page is available at https://github.com/Yewen1486/EMTAL.

For agents

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

get_harvested_code_for_paper("2501.06884")
get_code_for_paper("2501.06884")
have("2501.06884")

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

curl https://syntology.ai/api/ran/2501.06884.json

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

[![Syntology run record](https://syntology.ai/api/ran/2501.06884.svg)](https://syntology.ai/paper/2501.06884)

Connect an agent — have() is free.