SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.01753 · CVPR · 2024

Training-Free Pretrained Model Merging

Jie Song, Mingli Song, Zhengqi Xu, Yong Wang, Ke Yuan, Huiqiong Wang

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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, 0 violated it and 1 has no contract verdict; 2 failures of our instrument; 1 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/2403.01753.json · badge: /api/ran/2403.01753.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
zju-vipa/training_free_model_merging marked official in Papers with Code
Papers with Code archive
3 ran · 1 no recorded run
FunctionStatusWhere it lives
WeightFusion Ran
ran on a synthesized input · constructed an object; no result was computed
zju-vipa/training_free_model_merging/heterogeneous_tasks/mudsc.py
pointer only (licence: NONE) · get_code("ee4e6678eafd3832")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zju-vipa/training_free_model_merging 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.

refine_perm Ran
ran; our contract draft was wrong, not the code
zju-vipa/training_free_model_merging/heterogeneous_tasks/mudsc.py
pointer only (licence: NONE) · get_code("b7848359c35ca717")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zju-vipa/training_free_model_merging 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.

remove_col Ran
ran; our contract draft was wrong, not the code
zju-vipa/training_free_model_merging/heterogeneous_tasks/mudsc.py
pointer only (licence: NONE) · get_code("ac28dcec5c8aa992")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zju-vipa/training_free_model_merging 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.

CovarianceMetric Not yet run
unverified (harvested, no recorded run)
zju-vipa/training_free_model_merging/heterogeneous_tasks/mudsc.py
pointer only (licence: NONE) · get_code("bf4f3e9d597b9f91")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zju-vipa/training_free_model_merging 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 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 3 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
remove_col
brick of this paper's assembly: helper
1 other paper
1 later
2410.08589 (2024-10)
Retraining-Free Merging of Sparse MoE via Hierarchical Clustering

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 techniques have surfaced as a solution to combine multiple single-talent models into a single multi-talent model. However, previous endeavors in this field have either necessitated additional training or finetuning processes, or require that the models possess the same pre-trained initialization. In this work, we identify a common drawback in prior works w.r.t. the inconsistency of unit similarity in the weight space and the activation space. To address this inconsistency, we propose an innovative model merging framework, coined as merging under dual-space constraints (MuDSC). Specifically, instead of solely maximizing the objective of a single space, we advocate for the exploration of permutation matrices situated in a region with a unified high similarity in the dual space, achieved through the linear combination of activation and weight similarity matrices. In order to enhance usability, we have also incorporated adaptations for group structure, including Multi-Head Attention and Group Normalization. Comprehensive experimental comparisons demonstrate that MuDSC can significantly boost the performance of merged models with various task combinations and architectures. Furthermore, the visualization of the merged model within the multi-task loss landscape reveals that MuDSC enables the merged model to reside in the overlapping segment, featuring a unified lower loss for each task. Our code is publicly available at https://github.com/zju-vipa/training_free_model_merging.

For agents

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

get_harvested_code_for_paper("2403.01753")
get_code_for_paper("2403.01753")
have("2403.01753")

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

curl https://syntology.ai/api/ran/2403.01753.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.01753.svg)](https://syntology.ai/paper/2403.01753)

Connect an agent — have() is free.