SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2503.22178 · ICLR · 2025

AdaRank: Adaptive Rank Pruning for Enhanced Model Merging

Seunghoon Hong, Jiho Choi, Donggyun Kim, Chanhyuk Lee, Chanryeol Lee

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 (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 1 violated it and 1 has no contract verdict; 2 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/2503.22178.json · badge: /api/ran/2503.22178.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
david3684/adarank marked official in Papers with Code
Papers with Code archive
4 ran · 2 no recorded run
FunctionStatusWhere it lives
TaskVector Ran
ran on a synthesized input · constructed an object; no result was computed
david3684/adarank/lm/model_merging_methods/adarank_gpt2.py
pointer only (licence: NONE) · get_code("d24346902b4fa7e1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, david3684/adarank 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_exclude_regex Ran
ran; our contract draft was wrong, not the code
david3684/adarank/lm/model_merging_methods/adarank_gpt2.py
pointer only (licence: NONE) · get_code("64094ca096eebd1c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, david3684/adarank 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_param_names_to_merge Ran
ran; our contract draft was wrong, not the code
david3684/adarank/lm/model_merging_methods/adarank_gpt2.py
pointer only (licence: NONE) · get_code("840199cfb76e2913")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, david3684/adarank 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_mat_params Ran
ran, violated the contract we drafted
david3684/adarank/lm/model_merging_methods/adarank_gpt2.py
pointer only (licence: NONE) · get_code("25c594e39ce9e318")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, david3684/adarank 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.

AdaRankModule Not yet run
unverified (harvested, no recorded run)
david3684/adarank/lm/model_merging_methods/adarank_gpt2.py
pointer only (licence: NONE) · get_code("023a17baf96e0b3d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, david3684/adarank 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.

truncated_svd Not yet run
unverified (harvested, no recorded run)
david3684/adarank/lm/model_merging_methods/adarank_gpt2.py
pointer only (licence: NONE) · get_code("795a4a836a6ee6b5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, david3684/adarank 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, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 5 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_param_names_to_merge
brick of this paper's assembly: helper
4 other papers
2 dated earlier, 2 later
2212.04089 (2022-12)
Editing Models with Task Arithmetic
2408.03092 (2024-08)
Extend Model Merging from Fine-Tuned to Pre-Trained Large Language Models via Weight Disentanglement
2505.19892 (2025-05)
OptMerge: Unifying Multimodal LLM Capabilities and Modalities via Model Merging
and 1 more not named here

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

Model merging has emerged as a promising approach for unifying independently fine-tuned models into an integrated framework, significantly enhancing computational efficiency in multi-task learning. Recently, several SVD-based techniques have been introduced to exploit low-rank structures for enhanced merging, but their reliance on heuristically designed rank selection often leads to inter-task interference and suboptimal performance. In this paper, we propose AdaRank, a model merging framework that replaces this heuristic selection by adaptively selecting the beneficial singular components of task vectors to merge multiple models. We first show empirically that (i) selecting only the top singular components of task vectors can cause critical interference with other tasks, and (ii) assigning fixed ranks does not align with the varying complexity of tasks and layers. AdaRank addresses both issues by adapting per-component masks, indicating the selection of the component, to the unlabeled test data with entropy minimization. Our experimental findings show that AdaRank consistently improves existing merging methods across diverse backbones from different modalities, largely narrowing the performance gap against individually fine-tuned models.

For agents

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

get_harvested_code_for_paper("2503.22178")
get_code_for_paper("2503.22178")
have("2503.22178")

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

curl https://syntology.ai/api/ran/2503.22178.json

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

[![Syntology run record](https://syntology.ai/api/ran/2503.22178.svg)](https://syntology.ai/paper/2503.22178)

Connect an agent — have() is free.