SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.09353 · 2024

DoRA: Weight-Decomposed Low-Rank Adaptation

arXiv · PDF · Open in the Atlas

Code that ran

8 of 15 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; 8 failures of our instrument; 7 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/2402.09353.json · badge: /api/ran/2402.09353.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
NVlabs/DoRA canonical (classifier label)
classifier basis: plan_row
7 ran · 7 no recorded run
catid/dora reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
collate_fn Ran
ran; our contract draft was wrong, not the code
NVlabs/DoRA/image_video_text_understanding/feature_extraction/refcocog_mattnet.py
pointer only (licence: NONE) · get_code("68e41c28a6dfe81d")
How it ran

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

evaluate Ran
ran; our contract draft was wrong, not the code
NVlabs/DoRA/commonsense_reasoning/multi_dataset_eval.py
pointer only (licence: NONE) · get_code("2dc17f5e6fb39b3f")
How it ran

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

generate_data Ran
ran; our contract draft was wrong, not the code
catid/dora/dora.py
code served (permissive licence) · get_code("f040823d10747c45")
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 tuple. 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)

ARGS = {
    "num_samples": 2,
    "input_dim": 4,
}
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 tuple — a tuple 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
NVlabs/DoRA/commonsense_reasoning/finetune.py
pointer only (licence: NONE) · get_code("56e674752db00649")
How it ran

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

generate_prompt Ran
ran; our contract draft was wrong, not the code
NVlabs/DoRA/commonsense_reasoning/generate.py
pointer only (licence: NONE) · get_code("0dbc7fc6c518d0fb")
How it ran

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

generate_prompt Ran
ran; our contract draft was wrong, not the code
NVlabs/DoRA/commonsense_reasoning/commonsense_evaluate.py
pointer only (licence: NONE) · get_code("1c6b8be890b6118a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NVlabs/DoRA 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 Ran
ran; our contract draft was wrong, not the code
NVlabs/DoRA/commonsense_reasoning/commonsense_evaluate.py
pointer only (licence: NONE) · get_code("56a9466ff35b35bb")
How it ran

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

translate_state_dict_key Ran
ran; our contract draft was wrong, not the code
NVlabs/DoRA/commonsense_reasoning/export_state_dict_checkpoint.py
pointer only (licence: NONE) · get_code("a4f5d0414a1cf9c6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NVlabs/DoRA 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_peft_state_maybe_zero_3 Not yet run
unverified (harvested, no recorded run)
NVlabs/DoRA/visual_instruction_tuning/llava/train/train_dora.py
pointer only (licence: NOASSERTION) · get_code("0d95286fcf19dd47")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, NVlabs/DoRA (NOASSERTION). 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.

get_peft_state_non_dora_maybe_zero_3 Not yet run
unverified (harvested, no recorded run)
NVlabs/DoRA/visual_instruction_tuning/llava/train/train_dora.py
pointer only (licence: NOASSERTION) · get_code("293ec4b71aa63222")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, NVlabs/DoRA (NOASSERTION). 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.

main Not yet run
unverified (harvested, no recorded run)
NVlabs/DoRA/commonsense_reasoning/commonsense_evaluate.py
pointer only (licence: NONE); the stored copy get_code serves, from chitar/QuadEnhancer, is pointer only (licence: NONE) · get_code("415f46d8a341e28d")
How it ran

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

main Not yet run
unverified (harvested, no recorded run)
NVlabs/DoRA/commonsense_reasoning/evaluate.py
pointer only (licence: NONE); the stored copy get_code serves, from chitar/QuadEnhancer, is pointer only (licence: NONE) · get_code("3398969fc7af6ff7")
How it ran

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

maybe_zero_3 Not yet run
unverified (harvested, no recorded run)
NVlabs/DoRA/visual_instruction_tuning/llava/train/train_dora.py
pointer only (licence: NONE) · get_code("616ffbdc154ed2d8")
How it ran

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

permute Not yet run
unverified (harvested, no recorded run)
NVlabs/DoRA/commonsense_reasoning/export_state_dict_checkpoint.py
pointer only (licence: NONE) · get_code("a2f49e13f6e13d6b")
How it ran

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

unpermute Not yet run
unverified (harvested, no recorded run)
NVlabs/DoRA/commonsense_reasoning/export_state_dict_checkpoint.py
pointer only (licence: NONE) · get_code("6e275f232bbfb9b6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NVlabs/DoRA 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 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 12 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 2 the same month, 12 later) and 3 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
maybe_zero_3 37 other papers
4 dated earlier, 2 the same month, 31 later
2310.01779 (2023-10)
HallE-Control: Controlling Object Hallucination in Large Multimodal Models
2311.16839 (2023-11)
Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization
2312.02949 (2023-12)
LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models
and 34 more not named here
generate_prompt 15 other papers
3 dated earlier, 11 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
translate_state_dict_key 11 other papers
7 dated earlier, 4 later
2023.findings-emnlp.269 (2023 (year only))
An Empirical Study of Instruction-tuning Large Language Models in Chinese
2304.08177 (2023-04)
Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca
2305.00447 (2023-05)
TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation
and 8 more not named here
unpermute 11 other papers
7 dated earlier, 4 later
2023.findings-emnlp.269 (2023 (year only))
An Empirical Study of Instruction-tuning Large Language Models in Chinese
2304.08177 (2023-04)
Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca
2305.00447 (2023-05)
TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation
and 8 more not named here
load_data 10 other papers
2 dated earlier, 8 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
2406.11909 (2024-06)
Mixture-of-Subspaces in Low-Rank Adaptation
and 7 more not named here
generate_prompt 9 other papers
2 dated earlier, 7 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
2406.11909 (2024-06)
Mixture-of-Subspaces in Low-Rank Adaptation
and 6 more not named here
permute 9 other papers
5 dated earlier, 4 later
2023.findings-emnlp.269 (2023 (year only))
An Empirical Study of Instruction-tuning Large Language Models in Chinese
2305.00447 (2023-05)
TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation
2306.05064 (2023-06)
K2: A Foundation Language Model for Geoscience Knowledge Understanding and Utilization
and 6 more not named here
generate_prompt 5 other papers
2 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
2409.01035 (2024-09)
Task-Specific Directions: Definition, Exploration, and Utilization in Parameter Efficient Fine-Tuning
and 2 more not named here
collate_fn 3 other papers
1 dated earlier, 1 the same month, 1 later
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
2410.09437 (2024-10)
MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning
evaluate 3 other papers
3 later
2409.01035 (2024-09)
Task-Specific Directions: Definition, Exploration, and Utilization in Parameter Efficient Fine-Tuning
2510.03276 (2025-10)
QuadEnhancer: Leveraging Quadratic Transformations to Enhance Deep Neural Networks
2605.08110 (2026-05)
BaLoRA: Bayesian Low-Rank Adaptation of Large Scale Models
main 2 other papers
2 later
2409.01035 (2024-09)
Task-Specific Directions: Definition, Exploration, and Utilization in Parameter Efficient Fine-Tuning
2510.03276 (2025-10)
QuadEnhancer: Leveraging Quadratic Transformations to Enhance Deep Neural Networks
main 1 other paper
1 later
2510.03276 (2025-10)
QuadEnhancer: Leveraging Quadratic Transformations to Enhance Deep Neural Networks

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

Among the widely used parameter-efficient fine-tuning (PEFT) methods, LoRA and its variants have gained considerable popularity because of avoiding additional inference costs. However, there still often exists an accuracy gap between these methods and full fine-tuning (FT). In this work, we first introduce a novel weight decomposition analysis to investigate the inherent differences between FT and LoRA. Aiming to resemble the learning capacity of FT from the findings, we propose Weight-Decomposed Low-Rank Adaptation (DoRA). DoRA decomposes the pre-trained weight into two components, magnitude and direction, for fine-tuning, specifically employing LoRA for directional updates to efficiently minimize the number of trainable parameters. By employing \ours, we enhance both the learning capacity and training stability of LoRA while avoiding any additional inference overhead. \ours~consistently outperforms LoRA on fine-tuning LLaMA, LLaVA, and VL-BART on various downstream tasks, such as commonsense reasoning, visual instruction tuning, and image/video-text understanding. Code is available at https://github.com/NVlabs/DoRA.

For agents

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

get_harvested_code_for_paper("2402.09353")
get_code_for_paper("2402.09353")
have("2402.09353")

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

curl https://syntology.ai/api/ran/2402.09353.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.09353.svg)](https://syntology.ai/paper/2402.09353)

Connect an agent — have() is free.