SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.10673 · 2024

A Bayesian Interpretation of Adaptive Low-Rank Adaptation

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/2409.10673.json · badge: /api/ran/2409.10673.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
idiap/vilora canonical (classifier label)
classifier basis: census
4 ran · 2 no recorded run
FunctionStatusWhere it lives
bloom_model_postprocess_past_key_value Ran
ran; our contract draft was wrong, not the code
idiap/vilora/peft/src/peft/utils/constants.py
pointer only (licence: NONE) · get_code("ecf94b05123201e3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, idiap/vilora 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_if_peft_model Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
idiap/vilora/peft/src/peft/helpers.py
pointer only (licence: NONE); the stored copy get_code serves, from juyongjiang/KaSA, is pointer only (licence: NONE) · get_code("6a1220317ec3675f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, idiap/vilora 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_target_module_exists Ran
ran; our contract draft was wrong, not the code
idiap/vilora/peft/src/peft/tuners/tuners_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from juyongjiang/KaSA, is pointer only (licence: NONE) · get_code("c49fdcabd715ffef")
How it ran

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

is_torch_tpu_available Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
idiap/vilora/peft/src/peft/import_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from juyongjiang/KaSA, is pointer only (licence: NONE) · get_code("a3daaf3e5bdfc709")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, idiap/vilora 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_adapters_to_merge Not yet run
unverified (harvested, no recorded run)
idiap/vilora/peft/src/peft/tuners/tuners_utils.py
pointer only (licence: NONE) · get_code("212227da59ff7b87")
How it ran

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

starcoder_model_postprocess_past_key_value Not yet run
unverified (harvested, no recorded run)
idiap/vilora/peft/src/peft/utils/constants.py
pointer only (licence: NONE); the stored copy get_code serves, from juyongjiang/KaSA, is pointer only (licence: NONE) · get_code("249c10407ed14893")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, idiap/vilora 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, 6 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 6 later) and 0 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
is_torch_tpu_available 6 other papers
5 dated earlier, 1 later
2404.04316 (2024-04)
Parameter Efficient Quasi-Orthogonal Fine-Tuning via Givens Rotation
2405.12130 (2024-05)
MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning
2406.12629 (2024-06)
SeTAR: Out-of-Distribution Detection with Selective Low-Rank Approximation
and 3 more not named here
bloom_model_postprocess_past_key_value 5 other papers
3 dated earlier, 2 later
2405.12130 (2024-05)
MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning
2406.00132 (2024-06)
QuanTA: Efficient High-Rank Fine-Tuning of LLMs with Quantum-Informed Tensor Adaptation
2406.03792 (2024-06)
Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early Pruning
and 2 more not named here
check_if_peft_model 3 other papers
2 dated earlier, 1 later
2404.04316 (2024-04)
Parameter Efficient Quasi-Orthogonal Fine-Tuning via Givens Rotation
2408.15300 (2024-08)
GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs
2412.06071 (2024-12)
KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models
check_target_module_exists 2 other papers
1 dated earlier, 1 later
2405.12130 (2024-05)
MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning
2412.06071 (2024-12)
KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models
starcoder_model_postprocess_past_key_value 2 other papers
1 dated earlier, 1 later
2405.12130 (2024-05)
MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning
2412.06071 (2024-12)
KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models
check_adapters_to_merge 1 other paper
1 later
2412.06071 (2024-12)
KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models

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

Motivated by the sensitivity-based importance score of the adaptive low-rank adaptation (AdaLoRA), we utilize more theoretically supported metrics, including the signal-to-noise ratio (SNR), along with the Improved Variational Online Newton (IVON) optimizer, for adaptive parameter budget allocation. The resulting Bayesian counterpart not only has matched or surpassed the performance of using the sensitivity-based importance metric but is also a faster alternative to AdaLoRA with Adam. Our theoretical analysis reveals a significant connection between the two metrics, providing a Bayesian perspective on the efficacy of sensitivity as an importance score. Furthermore, our findings suggest that the magnitude, rather than the variance, is the primary indicator of the importance of parameters.

For agents

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

get_harvested_code_for_paper("2409.10673")
get_code_for_paper("2409.10673")
have("2409.10673")

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

curl https://syntology.ai/api/ran/2409.10673.json

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

[![Syntology run record](https://syntology.ai/api/ran/2409.10673.svg)](https://syntology.ai/paper/2409.10673)

Connect an agent — have() is free.