SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.06244 · ICLR · 2024

Quantifying and Enhancing Multi-modal Robustness with Modality Preference

Di Hu, Zequn Yang, Yake Wei, Ce Liang

arXiv · PDF · Open in the Atlas

Code that ran

9 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 4 failures of our instrument; 3 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/2402.06244.json · badge: /api/ran/2402.06244.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
GeWu-Lab/Certifiable-Robust-Multi-modal-Training canonical (classifier label)
classifier basis: census
6 ran · 3 no recorded run
gewu-lab/certifiable-robust-multi-modal-training canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
OWNNorm Ran
ran on a synthesized input · constructed an object; no result was computed
gewu-lab/certifiable-robust-multi-modal-training/models/fusion_model.py
pointer only (licence: NONE) · get_code("f445cc20cc72c61a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gewu-lab/certifiable-robust-multi-modal-training 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.

OrthFusion Ran
ran on a synthesized input · constructed an object; no result was computed
gewu-lab/certifiable-robust-multi-modal-training/models/fusion_model.py
pointer only (licence: NONE) · get_code("c96b174740a92073")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gewu-lab/certifiable-robust-multi-modal-training 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.

calculate_accuracy Ran
ran; our contract draft was wrong, not the code
GeWu-Lab/Certifiable-Robust-Multi-modal-Training/utils.py
pointer only (licence: NONE) · get_code("31ed62bbc034a89f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GeWu-Lab/Certifiable-Robust-Multi-modal-Training 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.

conv1x1 Ran
ran; our contract draft was wrong, not the code
GeWu-Lab/Certifiable-Robust-Multi-modal-Training/models/backbone.py
pointer only (licence: NONE) · get_code("d9def42110729a85")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GeWu-Lab/Certifiable-Robust-Multi-modal-Training 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
GeWu-Lab/Certifiable-Robust-Multi-modal-Training/models/backbone.py
pointer only (licence: NONE) · get_code("160bb14bd76201b4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GeWu-Lab/Certifiable-Robust-Multi-modal-Training 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.

get_lr Ran
ran, honoured the contract we drafted
GeWu-Lab/Certifiable-Robust-Multi-modal-Training/utils.py
pointer only (licence: NONE) · get_code("a11eecab8e7e04af")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GeWu-Lab/Certifiable-Robust-Multi-modal-Training 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.

inv_norm_tensor Ran
ran; our contract draft was wrong, not the code
GeWu-Lab/Certifiable-Robust-Multi-modal-Training/datasets/KS_dataset.py
pointer only (licence: NONE) · get_code("5dfe866366f3d5eb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GeWu-Lab/Certifiable-Robust-Multi-modal-Training 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.

orthogonal_linear Ran
ran on a synthesized input · constructed an object; no result was computed
gewu-lab/certifiable-robust-multi-modal-training/models/fusion_model.py
pointer only (licence: NONE) · get_code("158c46d01644f4c4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gewu-lab/certifiable-robust-multi-modal-training 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.

partialclass Ran
ran on a synthesized input
GeWu-Lab/Certifiable-Robust-Multi-modal-Training/utils.py
pointer only (licence: NONE) · get_code("0ab7cbcb8ecef516")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GeWu-Lab/Certifiable-Robust-Multi-modal-Training 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.

cal_for_frames Not yet run
unverified (harvested, no recorded run)
GeWu-Lab/Certifiable-Robust-Multi-modal-Training/pre-processing/extract_rgb_of.py
pointer only (licence: NONE) · get_code("7cfced1350c1f62a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GeWu-Lab/Certifiable-Robust-Multi-modal-Training 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.

compute_TVL1 Not yet run
unverified (harvested, no recorded run)
GeWu-Lab/Certifiable-Robust-Multi-modal-Training/pre-processing/extract_rgb_of.py
pointer only (licence: NONE) · get_code("1f7c7759ae51be72")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GeWu-Lab/Certifiable-Robust-Multi-modal-Training 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.

cross_modality_pretrain Not yet run
unverified (harvested, no recorded run)
GeWu-Lab/Certifiable-Robust-Multi-modal-Training/models/backbone.py
pointer only (licence: NONE) · get_code("e7f8e892b97e7abf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GeWu-Lab/Certifiable-Robust-Multi-modal-Training 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 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 2 the same month, 2 later) and 10 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
conv1x1 431 other papers
322 dated earlier, 7 the same month, 91 later, 10 same year, order not determinable, 1 undated · 38 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1506.01186 (2015-06)
Cyclical Learning Rates for Training Neural Networks
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
and 428 more not named here
conv3x3 312 other papers
221 dated earlier, 4 the same month, 76 later, 10 same year, order not determinable, 1 undated · 31 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
and 309 more not named here

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

Multi-modal models have shown a promising capability to effectively integrate information from various sources, yet meanwhile, they are found vulnerable to pervasive perturbations, such as uni-modal attacks and missing conditions. To counter these perturbations, robust multi-modal representations are highly expected, which are positioned well away from the discriminative multi-modal decision boundary. In this paper, different from conventional empirical studies, we focus on a commonly used joint multi-modal framework and theoretically discover that larger uni-modal representation margins and more reliable integration for modalities are essential components for achieving higher robustness. This discovery can further explain the limitation of multi-modal robustness and the phenomenon that multi-modal models are often vulnerable to attacks on the specific modality. Moreover, our analysis reveals how the widespread issue, that the model has different preferences for modalities, limits the multi-modal robustness by influencing the essential components and could lead to attacks on the specific modality highly effective. Inspired by our theoretical finding, we introduce a training procedure called Certifiable Robust Multi-modal Training (CRMT), which can alleviate this influence from modality preference and explicitly regulate essential components to significantly improve robustness in a certifiable manner. Our method demonstrates substantial improvements in performance and robustness compared with existing methods. Furthermore, our training procedure can be easily extended to enhance other robust training strategies, highlighting its credibility and flexibility. The code is available at https://github.com/GeWu-Lab/Certifiable-Robust-Multi-modal-Training.

For agents

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

get_harvested_code_for_paper("2402.06244")
get_code_for_paper("2402.06244")
have("2402.06244")

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

curl https://syntology.ai/api/ran/2402.06244.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.06244.svg)](https://syntology.ai/paper/2402.06244)

Connect an agent — have() is free.