SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.08245 · NeurIPS · 2024

Flex-MoE: Modeling Arbitrary Modality Combination via the Flexible Mixture-of-Experts

Tianlong Chen, Qi Long, Sukwon Yun, Inyoung Choi, Jie Peng, Yangfan Wu, Jingxuan Bao, Qiyiwen Zhang, Jiayi Xin

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, 1 violated it and 1 has no contract verdict; 1 failure of our instrument; 1 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/2410.08245.json · badge: /api/ran/2410.08245.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
UNITES-Lab/Flex-MoE canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
UNITES-Lab/flex-moe canonical (classifier label)
classifier basis: census
1 ran · 0 no recorded run
unites-lab/flex-moe community
Papers with Code archive
1 ran · 1 no recorded run
FunctionStatusWhere it lives
TransformerEncoderLayer Ran
ran on a synthesized input · constructed an object; no result was computed
unites-lab/flex-moe/models.py
pointer only (licence: NONE) · get_code("40e694fe9ff5b31a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, unites-lab/flex-moe 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.

convert_ids_to_index Ran
ran, violated the contract we drafted
UNITES-Lab/Flex-MoE/data.py
pointer only (licence: NONE) · get_code("9cc84aa4e66897c2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, UNITES-Lab/Flex-MoE 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.

setup_logger Ran
ran; our contract draft was wrong, not the code
UNITES-Lab/flex-moe/utils.py
pointer only (licence: NONE) · get_code("6b86acff8a357c55")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, UNITES-Lab/flex-moe 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.

FlexMoE Not yet run
unverified (harvested, no recorded run)
unites-lab/flex-moe/models.py
pointer only (licence: NONE) · get_code("fadc889a6ef30337")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, unites-lab/flex-moe 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, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 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.

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

Multimodal learning has gained increasing importance across various fields, offering the ability to integrate data from diverse sources such as images, text, and personalized records, which are frequently observed in medical domains. However, in scenarios where some modalities are missing, many existing frameworks struggle to accommodate arbitrary modality combinations, often relying heavily on a single modality or complete data. This oversight of potential modality combinations limits their applicability in real-world situations. To address this challenge, we propose Flex-MoE (Flexible Mixture-of-Experts), a new framework designed to flexibly incorporate arbitrary modality combinations while maintaining robustness to missing data. The core idea of Flex-MoE is to first address missing modalities using a new missing modality bank that integrates observed modality combinations with the corresponding missing ones. This is followed by a uniquely designed Sparse MoE framework. Specifically, Flex-MoE first trains experts using samples with all modalities to inject generalized knowledge through the generalized router (G-Router). The S-Router then specializes in handling fewer modality combinations by assigning the top-1 gate to the expert corresponding to the observed modality combination. We evaluate Flex-MoE on the ADNI dataset, which encompasses four modalities in the Alzheimer's Disease domain, as well as on the MIMIC-IV dataset. The results demonstrate the effectiveness of Flex-MoE, highlighting its ability to model arbitrary modality combinations in diverse missing modality scenarios. Code is available at: https://github.com/UNITES-Lab/flex-moe.

For agents

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

get_harvested_code_for_paper("2410.08245")
get_code_for_paper("2410.08245")
have("2410.08245")

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

curl https://syntology.ai/api/ran/2410.08245.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.08245.svg)](https://syntology.ai/paper/2410.08245)

Connect an agent — have() is free.