SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2307.08941 · ICML · 2023

MLP Fusion: Towards Efficient Fine-tuning of Dense and Mixture-of-Experts Language Models

Jingrui He, Yifan Chen, Tianxin Wei, Mengting Ai, Zeming Guo

arXiv · PDF · Open in the Atlas

Code that ran

10 of 14 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (5 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 4 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/2307.08941.json · badge: /api/ran/2307.08941.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
weitianxin/mlp_fusion canonical (classifier label)
classifier basis: classifier_2025
5 ran · 4 no recorded run
weitianxin/MLP_Fusion canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
FunctionStatusWhere it lives
Linear_sketch Ran
ran on a synthesized input · constructed an object; no result was computed
weitianxin/mlp_fusion/switch/switch_transformers/modeling_switch_transformers.py
pointer only (licence: NONE) · get_code("8e65852945fc41b9")
How it ran

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

Linear_svd Ran
ran on a synthesized input · constructed an object; no result was computed
weitianxin/mlp_fusion/switch/switch_transformers/modeling_switch_transformers.py
pointer only (licence: NONE) · get_code("51c5a7fc7ae52036")
How it ran

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

MMD_model Ran
ran on a synthesized input · constructed an object; no result was computed
weitianxin/mlp_fusion/switch/switch_transformers/modeling_switch_transformers.py
pointer only (licence: NONE) · get_code("0081b17668e7a074")
How it ran

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

ScaleLayer Ran
ran on a synthesized input · constructed an object; no result was computed
weitianxin/mlp_fusion/switch/switch_transformers/modeling_switch_transformers.py
pointer only (licence: NONE) · get_code("77ecf773c5c9651a")
How it ran

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

SwitchTransformersConfig Ran
ran on a synthesized input · constructed an object; no result was computed
weitianxin/mlp_fusion/switch/switch_transformers/modeling_switch_transformers.py
pointer only (licence: NONE) · get_code("905073406c036f74")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, weitianxin/mlp_fusion 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_position_ids_from_input_ids Ran
ran; our contract draft was wrong, not the code
weitianxin/MLP_Fusion/models/roberta/modeling_roberta.py
pointer only (licence: NONE); the stored copy get_code serves, from Kowsher/Propulsion, is pointer only (licence: NONE) · get_code("38f46ef4e03fee1c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, weitianxin/MLP_Fusion 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_position_ids_from_input_ids Ran
ran, honoured the contract we drafted
weitianxin/MLP_Fusion/models/roberta/modeling_flax_roberta.py
pointer only (licence: NONE) · get_code("6697ea7953dcb4c6")
How it ran

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

initial_val_plus_disturbance Ran
ran; our contract draft was wrong, not the code
weitianxin/MLP_Fusion/nlg/adapters/low_rank_layer.py
pointer only (licence: NONE) · get_code("9fea21a34c180fb0")
How it ran

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

top_filtering Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
weitianxin/MLP_Fusion/nlg/evaluate.py
pointer only (licence: NONE) · get_code("695eaa24be6f2a1d")
How it ran

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

truncated_gaussian Ran
ran; our contract draft was wrong, not the code
weitianxin/MLP_Fusion/nlg/adapters/low_rank_layer.py
pointer only (licence: NONE) · get_code("0178efd5619a35d7")
How it ran

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

SwitchTransformersDenseActDense Not yet run
unverified (harvested, no recorded run)
weitianxin/mlp_fusion/switch/switch_transformers/modeling_switch_transformers.py
pointer only (licence: NONE) · get_code("2005938ffe99509c")
How it ran

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

SwitchTransformersSparseMLP Not yet run
unverified (harvested, no recorded run)
weitianxin/mlp_fusion/switch/switch_transformers/modeling_switch_transformers.py
pointer only (licence: NONE) · get_code("18725727fe1cf6cb")
How it ran

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

SwitchTransformersTop1Router Not yet run
unverified (harvested, no recorded run)
weitianxin/mlp_fusion/switch/switch_transformers/modeling_switch_transformers.py
pointer only (licence: NONE) · get_code("a04df7ea135e2987")
How it ran

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

structure_prune Not yet run
unverified (harvested, no recorded run)
weitianxin/mlp_fusion/switch/switch_transformers/modeling_switch_transformers.py
pointer only (licence: NONE) · get_code("7c85bc322e1c67a7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, weitianxin/mlp_fusion 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 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 2 later) and 11 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
create_position_ids_from_input_ids 28 other papers
15 dated earlier, 11 later, 2 same year, order not determinable
2107.00910 (2021-07)
Learned Token Pruning for Transformers
2107.14035 (2021-07)
ProtoTransformer: A Meta-Learning Approach to Providing Student Feedback
2201.11732 (2022-01)
IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages
and 25 more not named here
top_filtering 7 other papers
6 dated earlier, 1 later
1901.08149 (2019-01)
TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents
1904.09751 (2019-04)
THE CURIOUS CASE OF NEURAL TEXT DeGENERATION
1911.00536 (2019-11)
DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation
and 4 more not named here
create_position_ids_from_input_ids 2 other papers
2 dated earlier
2202.07962 (2022-02)
Revisiting Parameter-Efficient Tuning: Are We Really There Yet?
2303.17395 (2023-03)
WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research

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

Fine-tuning a pre-trained language model (PLM) emerges as the predominant strategy in many natural language processing applications. However, this process is known to be expensive, especially on edge devices with low computing power. While general approaches (e.g. quantization and distillation) have been widely studied to reduce the compute/memory of PLM fine-tuning, one-shot compression techniques specifically designed for fine-tuning remain largely unexplored. In this paper, we investigate the neural tangent kernel (NTK)-which reveals the gradient descent dynamics of neural networks-of the multilayer perceptrons (MLP) modules in a PLM and propose to coin a lightweight PLM through NTK-approximating MLP fusion. By incorporating NTK into the compression process, MLP Fusion not only preserves the original model's output but also maintains its training dynamics. To achieve this, we reconsider the MLP as a bundle of sub-MLPs and cluster them into a given number of centroids, which can then be restored as a compressed MLP and surprisingly well approximate the NTK of the original PLM. Our approach is applicable to both standard MLP modules and Mixture-of-Experts (MoE) modules in PLMs, demonstrating its scalability and versatility. Additionally, we provide theoretical derivations to demonstrate how the proposed compression preserves the NTK. Extensive experiments of PLM fine-tuning on both natural language understanding and generation tasks are provided to verify the effectiveness of MLP fusion. Our code is available at https://github.com/weitianxin/MLP_Fusion.

For agents

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

get_harvested_code_for_paper("2307.08941")
get_code_for_paper("2307.08941")
have("2307.08941")

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

curl https://syntology.ai/api/ran/2307.08941.json

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

[![Syntology run record](https://syntology.ai/api/ran/2307.08941.svg)](https://syntology.ai/paper/2307.08941)

Connect an agent — have() is free.