SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.09946 · 2024

Low-Rank Interconnected Adaptation across Layers

arXiv · PDF · Open in the Atlas

Code that ran

9 of 13 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; 9 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/2407.09946.json · badge: /api/ran/2407.09946.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
yibozhong/lily canonical (classifier label)
classifier basis: census
9 ran · 4 no recorded run
FunctionStatusWhere it lives
determine_scheduler_type Ran
ran; our contract draft was wrong, not the code
yibozhong/lily/subject-driven-generation/train_lily.py
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, yibozhong/lily 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.

feed_forward_chunk_lily Ran
ran; our contract draft was wrong, not the code
yibozhong/lily/natural-language-understanding/lily.py
pointer only (licence: NONE) · get_code("f7d42195b9365611")
How it ran

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

forward_attn_lily Ran
ran; our contract draft was wrong, not the code
yibozhong/lily/natural-language-understanding/lily.py
pointer only (licence: NONE) · get_code("6e1edecf32659658")
How it ran

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

forward_attn_lily_kv Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yibozhong/lily/visual-adaptation-benchmark/vit/lily.py
pointer only (licence: NONE) · get_code("38a21650f4660a75")
How it ran

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

forward_mlp_lily Ran
ran; our contract draft was wrong, not the code
yibozhong/lily/visual-adaptation-benchmark/vit/lily.py
pointer only (licence: NONE) · get_code("7054afa64407297c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yibozhong/lily 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
yibozhong/lily/commonsense-reasoning/finetune_llama.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, yibozhong/lily 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
yibozhong/lily/commonsense-reasoning/evaluate_llama.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, yibozhong/lily 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
yibozhong/lily/commonsense-reasoning/evaluate_llama.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, yibozhong/lily 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.

prepare_model_for_int8_training Ran
ran; our contract draft was wrong, not the code
yibozhong/lily/commonsense-reasoning/finetune_mamba.py
pointer only (licence: NONE) · get_code("a9b94b97e3bc2c8c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yibozhong/lily 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)
yibozhong/lily/subject-driven-generation/train_lily.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, yibozhong/lily 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.

load_lily Not yet run
unverified (harvested, no recorded run)
yibozhong/lily/subject-driven-generation/infer_lily.py
pointer only (licence: NONE) · get_code("f7160c65cac52b2f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yibozhong/lily 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)
yibozhong/lily/commonsense-reasoning/evaluate_llama.py
pointer only (licence: NONE) · get_code("8e69377cf4c6f413")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yibozhong/lily 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)
yibozhong/lily/commonsense-reasoning/evaluate_mamba.py
pointer only (licence: NONE) · get_code("b0b4ac66dc9563ab")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yibozhong/lily 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 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 1 the same month, 4 later) and 8 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
5 dated earlier, 9 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
4 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 7 more not named here
generate_prompt 9 other papers
4 dated earlier, 5 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
3 dated earlier, 2 the same month, 2 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
2406.11909 (2024-06)
Mixture-of-Subspaces in Low-Rank Adaptation
and 4 more not named here
determine_scheduler_type 2 other papers
2 dated earlier
2403.16728 (2024-03)
Improving Diffusion Models's Data-Corruption Resistance using Scheduled Pseudo-Huber Loss
2406.11909 (2024-06)
Mixture-of-Subspaces in 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

Low-rank adaptation (LoRA) is a widely used parameter-efficient fine-tuning (PEFT) method that learns weight updates $ΔW = AB$ for pretrained weights $W$ through low-rank adapters $A$ and $B$. While LoRA ensures hardware efficiency, its low-rank weight updates limit adaptation performance. In this paper, we propose low-rank interconnected adaptation across layers (Lily), a novel PEFT method that introduces an interconnected framework with locally shared $A$ and globally shared $B$ experts. This structure eliminates redundant per-layer $AB$ pairs, enabling higher-rank $ΔW$ with equal or fewer parameters. To enhance expressiveness, we use data-dependent routers to determine $A$-$B$ interconnections, preventing $B$ experts from converging to the same behavior and improving representational power across domains. Experiments across modalities, architectures, and model sizes demonstrate Lily's superior performance and efficiency. GitHub: https://github.com/yibozhong/lily

For agents

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

get_harvested_code_for_paper("2407.09946")
get_code_for_paper("2407.09946")
have("2407.09946")

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

curl https://syntology.ai/api/ran/2407.09946.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.09946.svg)](https://syntology.ai/paper/2407.09946)

Connect an agent — have() is free.