SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2405.17461 · NeurIPS · 2024

EMR-MERGING: Tuning-Free High-Performance Model Merging

Xiangyu Yue, Wanli Ouyang, Tong He, Tao Chen, Chenyu Huang, Peng

arXiv · PDF · Open in the Atlas

Code that ran

13 of 15 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; 1 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 11 failures of our instrument; 2 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2405.17461.json · badge: /api/ran/2405.17461.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
harveyhuang18/emr_merging canonical (classifier label)
classifier basis: census
7 ran · 2 no recorded run
harveyhuang18/EMR_Merging canonical (classifier label)
classifier basis: classifier_2025
6 ran · 0 no recorded run
FunctionStatusWhere it lives
cola_tokenize_function Ran
ran; our contract draft was wrong, not the code
harveyhuang18/EMR_Merging/merge_lm/merge_gpt_glue.py
pointer only (licence: NONE) · get_code("a19cc1dfa848e7f9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harveyhuang18/EMR_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.

EMR_merge Ran
ran; our contract draft was wrong, not the code
harveyhuang18/EMR_Merging/merge_beit3/merge_beit.py
pointer only (licence: NONE) · get_code("94b554afac0917f0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harveyhuang18/EMR_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.

TA_merge Ran
ran; our contract draft was wrong, not the code
harveyhuang18/EMR_Merging/merge_beit3/merge_beit.py
pointer only (licence: NONE) · get_code("353d64feabe7458e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harveyhuang18/EMR_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.

add_ptm_to_tv Ran
ran; our contract draft was wrong, not the code
harveyhuang18/emr_merging/merge_vit/src/ties_merging_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from wzj1718/DiM3, is pointer only (licence: NONE) · get_code("860bf587f2fbf4e0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harveyhuang18/emr_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.

create_log_dir Ran
ran; our contract draft was wrong, not the code
harveyhuang18/emr_merging/merge_vit/src/main_emr_merging.py
pointer only (licence: NONE) · get_code("3053d2bdc3ea5c89")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harveyhuang18/emr_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.

emr_merge Ran
ran; our contract draft was wrong, not the code
harveyhuang18/emr_merging/merge_vit/src/main_emr_30_vits.py
pointer only (licence: NONE) · get_code("8d36051d98b72932")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harveyhuang18/emr_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.

eval_single_dataset Ran
ran on a synthesized input
harveyhuang18/emr_merging/merge_vit/src/main_emr_30_vits.py
pointer only (licence: NONE) · get_code("6398340aba15d719")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harveyhuang18/emr_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.

filt_param_to_merge Ran
ran; our contract draft was wrong, not the code
harveyhuang18/EMR_Merging/merge_beit3/merge_beit.py
pointer only (licence: NONE) · get_code("3a22253e8c88c3ce")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harveyhuang18/EMR_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.

mask_input_with_mask_rate Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
harveyhuang18/emr_merging/merge_lm/model_merging_methods/mask_weights_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from yule-BUAA/MergeLLM, is pointer only (licence: NONE) · get_code("99462e4ad36a59db")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harveyhuang18/emr_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.

mnli_tokenize_function Ran
ran; our contract draft was wrong, not the code
harveyhuang18/EMR_Merging/merge_lm/merge_gpt_glue.py
pointer only (licence: NONE) · get_code("fd703f1376ae3362")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harveyhuang18/EMR_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.

mrpc_tokenize_function Ran
ran; our contract draft was wrong, not the code
harveyhuang18/EMR_Merging/merge_lm/merge_gpt_glue.py
pointer only (licence: NONE) · get_code("637540089f33276d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harveyhuang18/EMR_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.

state_dict_to_vector Ran
ran, honoured the contract we drafted
harveyhuang18/emr_merging/merge_vit/src/ties_merging_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from thunlp-mt/adamms, is 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, harveyhuang18/emr_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.

vector_to_state_dict Ran
ran; our contract draft was wrong, not the code
harveyhuang18/emr_merging/merge_vit/src/ties_merging_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from thunlp-mt/adamms, is 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, harveyhuang18/emr_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.

create_log_dir Not yet run
unverified (harvested, no recorded run)
harveyhuang18/emr_merging/merge_vit/src/main_emr_30_vits.py
pointer only (licence: NONE) · get_code("5375fc5c7809c769")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harveyhuang18/emr_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.

normalize_word Not yet run
unverified (harvested, no recorded run)
harveyhuang18/emr_merging/merge_beit3/glossary.py
pointer only (licence: NONE) · get_code("8f1a44ab20956301")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harveyhuang18/emr_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 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 6 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 6 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
normalize_word 6 other papers
3 dated earlier, 3 later
2305.10722 (2023-05)
Discffusion: Discriminative Diffusion Models as Few-shot Vision and Language Learners
2310.00582 (2023-10)
Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs
2404.13039 (2024-04)
LaPA: Latent Prompt Assist Model For Medical Visual Question Answering
and 3 more not named here
create_log_dir 4 other papers
1 dated earlier, 3 later
2310.02575 (2023-10)
AdaMerging: Adaptive Model Merging for Multi-Task Learning
2407.07089 (2024-07)
Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic
2408.07362 (2024-08)
BadMerging: Backdoor Attacks Against Model Merging
and 1 more not named here
state_dict_to_vector 3 other papers
3 later
2410.14389 (2024-10)
SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgery
2503.23733 (2025-03)
AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization
2605.12960 (2026-05)
DiM 3 : Bridging Multilingual and Multimodal Models via Direction-and Magnitude-Aware Merging
add_ptm_to_tv 2 other papers
1 dated earlier, 1 later
2311.13171 (2023-11)
ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and Quantization
2605.12960 (2026-05)
DiM 3 : Bridging Multilingual and Multimodal Models via Direction-and Magnitude-Aware Merging
mask_input_with_mask_rate 2 other papers
1 dated earlier, 1 later
2311.03099 (2023-11)
Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
2408.03092 (2024-08)
Extend Model Merging from Fine-Tuned to Pre-Trained Large Language Models via Weight Disentanglement
vector_to_state_dict 2 other papers
2 later
2410.14389 (2024-10)
SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgery
2503.23733 (2025-03)
AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization

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

The success of pretrain-finetune paradigm brings about the release of numerous model weights. In this case, merging models finetuned on different tasks to enable a single model with multi-task capabilities is gaining increasing attention for its practicability. Existing model merging methods usually suffer from (1) significant performance degradation or (2) requiring tuning by additional data or training. In this paper, we rethink and analyze the existing model merging paradigm. We discover that using a single model's weights can hardly simulate all the models' performance. To tackle this issue, we propose ELECT, MASK & RESCALE-MERGING (EMR-MERGING). We first (a) elect a unified model from all the model weights and then (b) generate extremely light-weight task-specific modulators, including masks and rescalers, to align the direction and magnitude between the unified model and each specific model, respectively. EMR-MERGING is tuning-free, thus requiring no data availability or any additional training while showing impressive performance. We find that EMR-MERGING shows outstanding performance compared to existing merging methods under different classical and newly-established settings, including merging different numbers of vision models (up to 30), NLP models, PEFT models, and multi-modal models. 1

For agents

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

get_harvested_code_for_paper("2405.17461")
get_code_for_paper("2405.17461")
have("2405.17461")

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

curl https://syntology.ai/api/ran/2405.17461.json

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

[![Syntology run record](https://syntology.ai/api/ran/2405.17461.svg)](https://syntology.ai/paper/2405.17461)

Connect an agent — have() is free.