SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.09437 · 2024

MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning

arXiv · PDF · Open in the Atlas

Code that ran

5 of 9 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 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/2410.09437.json · badge: /api/ran/2410.09437.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
pumpkin-co/mtl-lora canonical (classifier label)
classifier basis: census
5 ran · 4 no recorded run
FunctionStatusWhere it lives
collate_fn Ran
ran; our contract draft was wrong, not the code
pumpkin-co/mtl-lora/image_text_understanding/feature_extraction/refcocog_mattnet.py
code served (permissive licence) · get_code("68e41c28a6dfe81d")
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. 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)

# Create a small batch of entries with the structure expected by collate_fn
batch = [
    {
        'img_id': 'img_001',
        'img': torch.randn(3, 32, 32),  # 3-channel image
        'boxes': torch.tensor([[10, 20, 30, 40], [50, 60, 70, 80]], dtype=torch.float32),  # 2 bounding boxes
        'captions': ['a dog', 'running']
    },
    {
        'img_id': 'img_002',
        'img': torch.randn(3, 32, 32),  # 3-channel image
        'boxes': torch.tensor([[5, 15, 25, 35]], dtype=torch.float32),  # 1 bounding box
        'captions': ['a cat']
    }
]

ARGS = {
    'batch': batch
}
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
create_batch Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
pumpkin-co/mtl-lora/mlora_evaluate.py
code served (permissive licence) · get_code("dcba3394053b84cd")
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. 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 numpy as np

torch.manual_seed(0)

# The function creates batches from a dataset
# It uses:
# - len(dataset) - so dataset needs __len__
# - dataset[i * batch_size : ...] - so dataset needs __getitem__ with slice support
# - Slicing should return a subset of the dataset

# Create a simple dataset-like object that supports len() and slicing
class SimpleDataset:
    def __init__(self, data):
        self.data = data
    
    def __len__(self):
        return len(self.data)
    
    def __getitem__(self, idx):
        if isinstance(idx, slice):
            return self.data[idx]
        return self.data[idx]

# Create a small dataset with 10 items
dataset = SimpleDataset([
    torch.randn(4),
    torch.randn(4),
    torch.randn(4),
    torch.randn(4),
    torch.randn(4),
    torch.randn(4),
    torch.randn(4),
    torch.randn(4),
    torch.randn(4),
    torch.randn(4),
])

batch_size = 3

ARGS = {
    "dataset": dataset,
    "batch_size": batch_size,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list output has no array shape of its own; none is 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
generate_prompt Ran
ran; our contract draft was wrong, not the code
pumpkin-co/mtl-lora/lora_finetune.py
code served (permissive licence) · get_code("56e674752db00649")
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 str. 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

torch.manual_seed(0)

# The function expects a dict with 'input', 'instruction', and 'output' keys
data_point = {
    'instruction': 'Translate the following text to French.',
    'input': 'Hello, how are you?',
    'output': 'Bonjour, comment allez-vous?'
}

ARGS = {
    'data_point': data_point
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
generate_prompt Ran
ran; our contract draft was wrong, not the code
pumpkin-co/mtl-lora/lora_evaluate.py
code served (permissive licence) · get_code("1c6b8be890b6118a")
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 str. 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

torch.manual_seed(0)

# The function generate_prompt takes two parameters:
# - instruction: a string describing a task
# - input: an optional string providing further context

instruction = "Translate the following text from English to French."
input_text = "Hello, how are you?"

ARGS = {
    "instruction": instruction,
    "input": input_text
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
lora_state_dict Ran
ran; our contract draft was wrong, not the code
pumpkin-co/mtl-lora/image_text_understanding/VL-T5/src/lora/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from shihaohou/FedPuReL, is pointer only (licence: NONE) · get_code("660073ae6862ac6e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from shihaohou/FedPuReL, 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.

load_data Not yet run
unverified (harvested, no recorded run)
pumpkin-co/mtl-lora/lora_evaluate.py
code served (permissive licence) · get_code("1d07463312991f52")
How it ran

no invocation recorded.

main Not yet run
unverified (harvested, no recorded run)
pumpkin-co/mtl-lora/lora_evaluate.py
code served (permissive licence) · get_code("9b2aa09fa1644193")
How it ran

no invocation recorded.

train Not yet run
unverified (harvested, no recorded run)
pumpkin-co/mtl-lora/lora_finetune.py
code served (permissive licence) · get_code("6cf4a819aa35986b")
How it ran

no invocation recorded.

train Not yet run
unverified (harvested, no recorded run)
pumpkin-co/mtl-lora/lora_finetune_single.py
code served (permissive licence) · get_code("823409f0ab13f67c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 2 the same month, 3 later) and 5 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
generate_prompt 15 other papers
7 dated earlier, 3 the same month, 4 later, 1 same year, order not determinable
2304.01933 (2023-04)
LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models
2307.08072 (2023-07)
Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical Study
2024.naacl-long.132 (2024 (year only))
LLM-based Medical Assistant Personalization with Short-and Long-Term Memory Coordination
and 12 more not named here
lora_state_dict 13 other papers
8 dated earlier, 1 the same month, 3 later, 1 same year, order not determinable
2202.00535 (2022-02)
Novelty Controlled Paraphrase Generation with Retrieval Augmented Conditional Prompt Tuning
2202.07962 (2022-02)
Revisiting Parameter-Efficient Tuning: Are We Really There Yet?
2211.09790 (2022-11)
ConStruct-VL: Data-Free Continual Structured VL Concepts Learning
and 10 more not named here
generate_prompt 9 other papers
6 dated earlier, 3 later
2304.01933 (2023-04)
LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models
2401.00788 (2024-01)
Astraios: Parameter-Efficient Instruction Tuning Code Large Language Models
2402.09353 (2024-02)
DoRA: Weight-Decomposed Low-Rank Adaptation
and 6 more not named here
collate_fn 3 other papers
3 dated earlier
Zhang_VQACL_A_Novel_Visual_Question_Answering_Continual_Learning_Setting_CVPR_2023_paper (2023 (year only))
VQACL: A Novel Visual Question Answering Continual Learning Setting
2402.07742 (2024-02)
Asking Multimodal Clarifying Questions in Mixed-Initiative Conversational Search
2402.09353 (2024-02)
DoRA: Weight-Decomposed Low-Rank Adaptation

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

Parameter-efficient fine-tuning (PEFT) has been widely employed for domain adaptation, with LoRA being one of the most prominent methods due to its simplicity and effectiveness. However, in multi-task learning (MTL) scenarios, LoRA tends to obscure the distinction between tasks by projecting sparse high-dimensional features from different tasks into the same dense low-dimensional intrinsic space. This leads to task interference and suboptimal performance for LoRA and its variants. To tackle this challenge, we propose MTL-LoRA, which retains the advantages of low-rank adaptation while significantly enhancing MTL capabilities. MTL-LoRA augments LoRA by incorporating additional task-adaptive parameters that differentiate task-specific information and capture shared knowledge across various tasks within low-dimensional spaces. This approach enables pre-trained models to jointly adapt to different target domains with a limited number of trainable parameters. Comprehensive experimental results, including evaluations on public academic benchmarks for natural language understanding, commonsense reasoning, and image-text understanding, as well as real-world industrial text Ads relevance datasets, demonstrate that MTL-LoRA outperforms LoRA and its various variants with comparable or even fewer learnable parameters in MTL setting.

For agents

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

get_harvested_code_for_paper("2410.09437")
get_code_for_paper("2410.09437")
have("2410.09437")

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

curl https://syntology.ai/api/ran/2410.09437.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.09437.svg)](https://syntology.ai/paper/2410.09437)

Connect an agent — have() is free.