SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2501.01240 · AAAI · 2025

Asymmetric Reinforcing Against Multi-Modal Representation Bias

Qinghua Hu, Bing Cao, Nannan Wang, Pengfei Zhu, Xiyuan Gao

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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 0 have no contract verdict; 2 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/2501.01240.json · badge: /api/ran/2501.01240.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
gao-xiyuan/arm marked official in Papers with Code
Papers with Code archive
3 ran · 0 no recorded run
FunctionStatusWhere it lives
compute_joint_prob Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
gao-xiyuan/arm/mmpretrain/models/necks/MI_tool.py
pointer only (licence: NONE) · get_code("0a34039861ba785c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gao-xiyuan/arm 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.

compute_marginal_prob Ran
ran, honoured the contract we drafted
gao-xiyuan/arm/mmpretrain/models/necks/MI_tool.py
pointer only (licence: NONE) · get_code("f60103ae6ab33f5a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gao-xiyuan/arm 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.

mutual_information Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
gao-xiyuan/arm/mmpretrain/models/necks/MI_tool.py
pointer only (licence: NONE) · get_code("915c0c262c871eef")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gao-xiyuan/arm 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 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 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.

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 strength of multimodal learning lies in its ability to integrate information from various sources, providing rich and comprehensive insights. However, in real-world scenarios, multi-modal systems often face the challenge of dynamic modality contributions, the dominance of different modalities may change with the environments, leading to suboptimal performance in multimodal learning. Current methods mainly enhance weak modalities to balance multimodal representation bias, which inevitably optimizes from a partialmodality perspective, easily leading to performance descending for dominant modalities. To address this problem, we propose an Asymmetric Reinforcing method against Multimodal representation bias (ARM). Our ARM dynamically reinforces the weak modalities while maintaining the ability to represent dominant modalities through conditional mutual information. Moreover, we provide an in-depth analysis that optimizing certain modalities could cause information loss and prevent leveraging the full advantages of multimodal data. By exploring the dominance and narrowing the contribution gaps between modalities, we have significantly improved the performance of multimodal learning, making notable progress in mitigating imbalanced multimodal learning.

For agents

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

get_harvested_code_for_paper("2501.01240")
get_code_for_paper("2501.01240")
have("2501.01240")

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

curl https://syntology.ai/api/ran/2501.01240.json

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

[![Syntology run record](https://syntology.ai/api/ran/2501.01240.svg)](https://syntology.ai/paper/2501.01240)

Connect an agent — have() is free.