SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2503.23733 · CVPR · 2025

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization

Yang Liu, Peng Li, Ming Yan, Maosong Sun, Fei Huang, Zhifang Sui, Ji Zhang, Jiabo Ye, Xiaochen Wang, Chi Chen, Yiru Wang, Yiyang Du

arXiv · PDF · Open in the Atlas

Code that ran

8 of 8 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; 6 failures of our instrument; 0 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/2503.23733.json · badge: /api/ran/2503.23733.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
thunlp-mt/adamms marked official in Papers with Code
Papers with Code archive
8 ran · 0 no recorded run
FunctionStatusWhere it lives
disjoint_merge Ran
ran; our contract draft was wrong, not the code
thunlp-mt/adamms/merge/ties_merging.py
pointer only (licence: NONE) · get_code("9a0346fac1c94b40")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thunlp-mt/adamms 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.

do_merging_strategy Ran
ran; our contract draft was wrong, not the code
thunlp-mt/adamms/merge/ties_merging.py
pointer only (licence: NONE) · get_code("13f5811639b2bd71")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thunlp-mt/adamms 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.

resolve_sign Ran
ran, honoured the contract we drafted
thunlp-mt/adamms/merge/ties_merging.py
pointer only (licence: NONE) · get_code("843a0f021c3f85d2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thunlp-mt/adamms 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.

resolve_zero_signs Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
thunlp-mt/adamms/merge/ties_merging.py
pointer only (licence: NONE) · get_code("860408c2bd01950e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thunlp-mt/adamms 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.

state_dict_to_vector Ran
ran, honoured the contract we drafted
thunlp-mt/adamms/merge/ties_merging.py
pointer only (licence: NONE) · get_code("72391ca34e9a8cfe")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thunlp-mt/adamms 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.

ties_merging Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
thunlp-mt/adamms/merge/ties_merging.py
pointer only (licence: NONE) · get_code("9b2cd521bf6db9bf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thunlp-mt/adamms 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.

topk_values_mask Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
thunlp-mt/adamms/merge/ties_merging.py
pointer only (licence: NONE) · get_code("9f4ac26be542f539")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thunlp-mt/adamms 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.

vector_to_state_dict Ran
ran; our contract draft was wrong, not the code
thunlp-mt/adamms/merge/ties_merging.py
pointer only (licence: NONE) · get_code("bf6efec91354af72")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thunlp-mt/adamms 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 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 2 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
resolve_zero_signs
brick of this paper's assembly: helper
5 other papers
3 dated earlier, 2 later · 4 only as an assembly brick
2306.01708 (2023-06)
TIES-MERGING: Resolving Interference When Merging Models
2406.11801 (2024-06)
Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations
2410.19735 (2024-10)
Model merging with SVD to tie the Knots
and 2 more not named here
state_dict_to_vector
brick of this paper's assembly: helper
3 other papers
2 dated earlier, 1 later
2405.17461 (2024-05)
EMR-MERGING: Tuning-Free High-Performance Model Merging
2410.14389 (2024-10)
SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgery
2605.12960 (2026-05)
DiM 3 : Bridging Multilingual and Multimodal Models via Direction-and Magnitude-Aware Merging
resolve_sign
brick of this paper's assembly: helper
2 other papers
2 dated earlier · 2 only as an assembly brick
2306.01708 (2023-06)
TIES-MERGING: Resolving Interference When Merging Models
2406.11801 (2024-06)
Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations
vector_to_state_dict
brick of this paper's assembly: helper
2 other papers
2 dated earlier
2405.17461 (2024-05)
EMR-MERGING: Tuning-Free High-Performance Model Merging
2410.14389 (2024-10)
SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgery

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

Recently, model merging methods have demonstrated powerful strengths in combining abilities on various tasks from multiple Large Language Models (LLMs). While previous model merging methods mainly focus on merging homogeneous models with identical architecture, they meet challenges when dealing with Multimodal Large Language Models (MLLMs) with inherent heterogeneous property, including differences in model architecture and the asymmetry in the parameter space. In this work, we propose AdaMMS 1 , a novel model merging method tailored for heterogeneous MLLMs. Our method tackles the challenges in three steps: mapping, merging and searching. Specifically, we first design mapping function between models to apply model merging on MLLMs with different architecture. Then we apply linear interpolation on model weights to actively adapt the asymmetry in the heterogeneous MLLMs. Finally in the hyper-parameter searching step, we propose an unsupervised hyper-parameter selection method for model merging. As the first model merging method capable of merging heterogeneous MLLMs without labeled data, extensive experiments on various model combinations demonstrated that AdaMMS outperforms previous model merging methods on various vision-language benchmarks. 2 * Equal contribution.

For agents

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

get_harvested_code_for_paper("2503.23733")
get_code_for_paper("2503.23733")
have("2503.23733")

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

curl https://syntology.ai/api/ran/2503.23733.json

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

[![Syntology run record](https://syntology.ai/api/ran/2503.23733.svg)](https://syntology.ai/paper/2503.23733)

Connect an agent — have() is free.