SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.11943 · 2024

Benchmarking Large Multimodal Models against Common Corruptions

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure 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/2401.11943.json · badge: /api/ran/2401.11943.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
sail-sg/mmcbench canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
compute_similarities Ran
ran; our contract draft was wrong, not the code
sail-sg/mmcbench/text2image/evaluate.py
code served (permissive licence) · get_code("d6bf975f8ec0d91f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
import pandas as pd
from PIL import Image
import numpy as np

torch.manual_seed(0)

# Stand-in CLIP model that mimics the real CLIP interface
class MockCLIPModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.embed_dim = 4
        self.image_proj = nn.Linear(3, 4)
        self.text_proj = nn.Linear(3, 4)
    
    def encode_image(self, images):
        # images: (batch, 3, H, W) -> output: (batch, embed_dim)
        batch_size = images.shape[0]
        return self.image_proj(torch.randn(batch_size, 3))
    
    def encode_text(self, text_tokens):
        # text_tokens: (batch, seq_len) -> output: (batch, embed_dim)
        batch_size = text_tokens.shape[0]
        return self.text_proj(torch.randn(batch_size, 3))

# Stand-in tokenizer
class MockTokenizer:
    def __call__(self, captions):
        # Return a tensor of shape (batch_size, seq_len)
        batch_size = len(captions)
        seq_len = 10
        return torch.randint(0, 100, (batch_size, seq_len))

# Stand-in preprocessing function
class MockPreprocess:
    def __call__(self, img):
        # Convert PIL image to tensor (3, H, W) with values in [0, 1]
        img_array = np.array(img)
        return torch.from_numpy(img_array).permute(2, 0, 1).float() / 255.0

# Stand-in image generation model
class MockImageModel(nn.Module):
    def __init__(self):
        super().__init__()
    
    def __call__(self, captions):
        # Generate small PIL images
        batch_size = len(captions)
        images = []
        for _ in range(batch_size):
            # Create a small RGB image
            img_array = np.random.randint(0, 256, (64, 64, 3), dtype=np.uint8)
            img = Image.fromarray(img_array, mode='RGB')
            images.append(img)
        return images

# Stand-in args object
class MockArgs:
    def __init__(self):
        self.store_output = True

# Create the DataFrame chunk with captions and corruption methods
chunk = pd.DataFrame({
    'key': ['img_0', 'img_1'],
    'caption': ['a red cat', 'a blue dog'],
    'typo': ['a red cat typo', 'a blue dog typo'],
    'paraphrase': ['a cat that is red', 'a dog that is blue']
})

# Construct ARGS
ARGS = {
    'chunk': chunk,
    'model': MockImageModel(),
    'clip_model': MockCLIPModel(),
    'device': torch.device('cpu'),
    'clip_tokenizer': MockTokenizer(),
    'clip_preprocess': MockPreprocess(),
    'args': MockArgs()
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, pandas, torch, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 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 1 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

This technical report aims to fill a deficiency in the assessment of large multimodal models (LMMs) by specifically examining the self-consistency of their outputs when subjected to common corruptions. We investigate the cross-modal interactions between text, image, and speech, encompassing four essential generation tasks: text-to-image, image-to-text, text-to-speech, and speech-to-text. We create a comprehensive benchmark, named MMCBench, that covers more than 100 popular LMMs (totally over 150 model checkpoints). A thorough evaluation under common corruptions is critical for practical deployment and facilitates a better understanding of the reliability of cutting-edge LMMs. The benchmarking code is available at https://github.com/sail-sg/MMCBench

For agents

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

get_harvested_code_for_paper("2401.11943")
get_code_for_paper("2401.11943")
have("2401.11943")

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

curl https://syntology.ai/api/ran/2401.11943.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.11943.svg)](https://syntology.ai/paper/2401.11943)

Connect an agent — have() is free.