SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.01267 · ICML · 2026

Diving into Kronecker Adapters: Component Design Matters

Zhenyu Liao, Feng Zhou, Zenan Ling, Robert Qiu, Jiayu Bai, Tianqi Hou, Danchen Yu

arXiv · PDF · Open in the Atlas

Code that ran

11 of 11 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 9 failures of our instrument; 0 no recorded run), measured 2026-11-22; 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/2602.01267.json · badge: /api/ran/2602.01267.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
rainstonee/CDKA canonical (classifier label)
classifier basis: census
11 ran · 0 no recorded run
FunctionStatusWhere it lives
SeqToSeqEncode Ran
ran; our contract draft was wrong, not the code
rainstonee/CDKA/utils.py
pointer only (licence: NONE) · get_code("45db30ac52f3cd6d")
How it ran

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

cache_to_disk Ran
ran; our contract draft was wrong, not the code
rainstonee/CDKA/data.py
pointer only (licence: NONE) · get_code("1d0db22ae067b53c")
How it ran

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

causalLMEncode Ran
ran; our contract draft was wrong, not the code
rainstonee/CDKA/utils.py
pointer only (licence: NONE) · get_code("38de4191703bb96a")
How it ran

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

extract_num Ran
ran, honoured the contract we drafted
rainstonee/CDKA/eval_gsm8k.py
pointer only (licence: NONE) · get_code("1b53cbd93e0bc5fb")
How it ran

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

find_all_linear_modules Ran
ran; our contract draft was wrong, not the code
rainstonee/CDKA/run_exp.py
pointer only (licence: NONE) · get_code("65f3cc97d3e5034f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rainstonee/CDKA 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_forward_hook Ran
ran; our contract draft was wrong, not the code
rainstonee/CDKA/logTrainer.py
pointer only (licence: NONE) · get_code("fd33ad9ae547c836")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rainstonee/CDKA 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_module Ran
ran; our contract draft was wrong, not the code
rainstonee/CDKA/lora_plus.py
pointer only (licence: NONE) · get_code("ef1ba16faaacbb49")
How it ran

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

kron Ran
ran, honoured the contract we drafted
rainstonee/CDKA/run_exp.py
pointer only (licence: NONE) · get_code("75a18bb7fe426341")
How it ran

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

modified_gram_schmidt Ran
ran; our contract draft was wrong, not the code
rainstonee/CDKA/run_exp.py
pointer only (licence: NONE) · get_code("872ad60fac6c3527")
How it ran

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

post_process Ran
ran; our contract draft was wrong, not the code
rainstonee/CDKA/eval_humaneval.py
pointer only (licence: NONE) · get_code("48720117c27620bc")
How it ran

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

rebuild Ran
ran; our contract draft was wrong, not the code
rainstonee/CDKA/split.py
pointer only (licence: NONE) · get_code("86f83d0db1b0bd2d")
How it ran

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

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 0 the same month, 0 later) and 4 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
get_module 4 other papers
4 dated earlier
2312.00700 (2023-12)
WeGeFT: Weight-Generative Fine-Tuning for Multi-Faceted Efficient Adaptation of Large Models
2402.12354 (2024-02)
LoRA+: Efficient Low Rank Adaptation of Large Models
2407.05000 (2024-07)
LoRA-GA: Low-Rank Adaptation with Gradient Approximation
and 1 more not named here
SeqToSeqEncode 2 other papers
2 dated earlier
2312.00700 (2023-12)
WeGeFT: Weight-Generative Fine-Tuning for Multi-Faceted Efficient Adaptation of Large Models
2508.19564 (2025-08)
Bi-LoRA: Efficient Sharpness-Aware Minimization for Fine-Tuning Large-Scale Models
cache_to_disk 2 other papers
2 dated earlier
2312.00700 (2023-12)
WeGeFT: Weight-Generative Fine-Tuning for Multi-Faceted Efficient Adaptation of Large Models
2508.19564 (2025-08)
Bi-LoRA: Efficient Sharpness-Aware Minimization for Fine-Tuning Large-Scale Models
causalLMEncode 2 other papers
2 dated earlier
2312.00700 (2023-12)
WeGeFT: Weight-Generative Fine-Tuning for Multi-Faceted Efficient Adaptation of Large Models
2508.19564 (2025-08)
Bi-LoRA: Efficient Sharpness-Aware Minimization for Fine-Tuning Large-Scale Models
find_all_linear_modules 2 other papers
2 dated earlier
2312.00700 (2023-12)
WeGeFT: Weight-Generative Fine-Tuning for Multi-Faceted Efficient Adaptation of Large Models
2508.19564 (2025-08)
Bi-LoRA: Efficient Sharpness-Aware Minimization for Fine-Tuning Large-Scale Models
post_process 2 other papers
2 dated earlier
2312.00700 (2023-12)
WeGeFT: Weight-Generative Fine-Tuning for Multi-Faceted Efficient Adaptation of Large Models
2408.04556 (2024-08)
BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models
get_forward_hook 1 other paper
1 dated earlier
2312.00700 (2023-12)
WeGeFT: Weight-Generative Fine-Tuning for Multi-Faceted Efficient Adaptation of Large 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

Kronecker adapters have emerged as a promising approach for fine-tuning large-scale models, enabling high-rank updates through tunable component structures. However, existing work largely treats the component structure as a fixed or heuristic design choice, leaving the dimensions and number of Kronecker components underexplored. In this paper, we identify component structure as a key factor governing the capacity of Kronecker adapters. We perform a fine-grained analysis of both the dimensions and number of Kronecker components. In particular, we show that the alignment between Kronecker adapters and full fine-tuning depends on component configurations. Guided by these insights, we propose Component Designed Kronecker Adapters (CDKA). We further provide parameter-budgetaware configuration guidelines and a tailored training stabilization strategy for practical deployment. Experiments across various architectures and modalities demonstrate the effectiveness of CDKA. Code is available at https: //github.com/rainstonee/CDKA.

For agents

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

get_harvested_code_for_paper("2602.01267")
get_code_for_paper("2602.01267")
have("2602.01267")

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

curl https://syntology.ai/api/ran/2602.01267.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.01267.svg)](https://syntology.ai/paper/2602.01267)

Connect an agent — have() is free.