SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.11909 · EMNLP · 2024

Mixture-of-Subspaces in Low-Rank Adaptation

Zhe Zhao, Jiahao Wang, Ngai Wong, Taiqiang Wu

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 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; 4 failures of our instrument; 2 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/2406.11909.json · badge: /api/ran/2406.11909.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
wutaiqiang/moslora canonical (classifier label)
classifier basis: census
4 ran · 2 no recorded run
FunctionStatusWhere it lives
determine_scheduler_type Ran
ran; our contract draft was wrong, not the code
wutaiqiang/moslora/subject_driven_generation/train_dreambooth_lora_sdxl.py
pointer only (licence: NONE); the stored copy get_code serves, from yibozhong/lily, is pointer only (licence: NONE) · get_code("03e1c6795642a8db")
How it ran

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

import_model_class_from_model_name_or_path Not yet run
unverified (harvested, no recorded run)
wutaiqiang/moslora/subject_driven_generation/train_dreambooth_lora_sdxl.py
pointer only (licence: NONE); the stored copy get_code serves, from kwongihyun/tweediemix, is pointer only (licence: NONE) · get_code("86965b6bae051ea4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wutaiqiang/moslora 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)
wutaiqiang/moslora/commonsense_reasoning/commonsense_evaluate.py
pointer only (licence: NONE) · get_code("b8da7d64c2442014")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wutaiqiang/moslora 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 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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, 5 later) and 1 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
4 dated earlier, 10 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
load_data 10 other papers
3 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
2402.09353 (2024-02)
DoRA: Weight-Decomposed Low-Rank Adaptation
and 7 more not named here
generate_prompt 9 other papers
3 dated earlier, 6 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
import_model_class_from_model_name_or_path 7 other papers
2 dated earlier, 5 later
2403.14572 (2024-03)
Implicit Style-Content Separation using B-LoRA
2405.13637 (2024-05)
Curriculum Direct Preference Optimization for Diffusion and Consistency Models
2407.04604 (2024-07)
PartCraft: Crafting Creative Objects by Parts
and 4 more not named here
determine_scheduler_type 2 other papers
1 dated earlier, 1 later
2403.16728 (2024-03)
Improving Diffusion Models's Data-Corruption Resistance using Scheduled Pseudo-Huber Loss
2407.09946 (2024-07)
Low-Rank Interconnected Adaptation across Layers

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

In this paper, we introduce a subspace-inspired Low-Rank Adaptation (LoRA) method, which is computationally efficient, easy to implement, and readily applicable to large language, multimodal, and diffusion models. Initially, we equivalently decompose the weights of LoRA into two subspaces, and find that simply mixing them can enhance performance. To study such a phenomenon, we revisit it through a fine-grained subspace lens, showing that such modification is equivalent to employing a fixed mixer to fuse the subspaces. To be more flexible, we jointly learn the mixer with the original LoRA weights, and term the method as Mixtureof-Subspaces LoRA (MoSLoRA). MoSLoRA consistently outperforms LoRA on tasks in different modalities, including commonsense reasoning, visual instruction tuning, and subjectdriven text-to-image generation, demonstrating its effectiveness and robustness. Codes are available at github.

For agents

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

get_harvested_code_for_paper("2406.11909")
get_code_for_paper("2406.11909")
have("2406.11909")

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

curl https://syntology.ai/api/ran/2406.11909.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.11909.svg)](https://syntology.ai/paper/2406.11909)

Connect an agent — have() is free.