SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · Wang_Distribution-Consistent_Modal_Recovering_for_Incomplete_Multimodal_Learning_ICCV_2023_paper · ICCV · 2023

Distribution-Consistent Modal Recovering for Incomplete Multimodal Learning

Yong Li, Yuanzhi Wang, Zhen Cui

Open in the Atlas

Code that ran

6 of 7 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; 3 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 2 failures of our instrument; 1 no recorded run), measured 2026-11-22; 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/Wang_Distribution-Consistent_Modal_Recovering_for_Incomplete_Multimodal_Learning_ICCV_2023_paper.json · badge: /api/ran/Wang_Distribution-Consistent_Modal_Recovering_for_Incomplete_Multimodal_Learning_ICCV_2023_paper.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
mdswyz/DiCMoR canonical (classifier label)
classifier basis: census
6 ran · 1 no recorded run
FunctionStatusWhere it lives
compute_unconditional_prior Ran
ran on a synthesized input
mdswyz/DiCMoR/trains/singleTask/model/glow.py
code served (permissive licence) · get_code("6385eaa93d83fecd")
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 Normal. 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

torch.manual_seed(0)

# Construct a valid argument for z
# The function expects a tensor and calls:
# - z.new_zeros(z.shape) - creates a zero tensor of same shape
# - z.shape - accesses the shape attribute
# - torch.exp(h) - exponential function
# So z should be a regular tensor

z = torch.randn(2, 4)

ARGS = {
    "z": z
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Normal — a Normal output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Normal output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
count_parameters Ran
ran, honoured the contract we drafted
mdswyz/DiCMoR/utils/functions.py
code served (permissive licence) · get_code("0d68bc7ea92abc88")
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 int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        return self.linear2(self.linear1(x))

model = SimpleModel()

ARGS = {
    "model": model
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
dict_to_str Ran
ran; our contract draft was wrong, not the code
mdswyz/DiCMoR/utils/functions.py
code served (permissive licence) · get_code("c8423ee1916002d8")
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 str. 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

def dict_to_str(src_dict):
    dst_str = ''
    for key in src_dict.keys():
        dst_str += ' %s: %.4f ' % (key, src_dict[key])
    return dst_str

ARGS = {
    'src_dict': {
        'loss': 0.5234,
        'accuracy': 0.9876,
        'precision': 0.8765
    }
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
gaussian_log_p Ran
ran, honoured the contract we drafted
mdswyz/DiCMoR/trains/singleTask/model/glow.py
code served (permissive licence) · get_code("0466e4f918aa9da0")
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 Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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
from math import log, pi, exp

torch.manual_seed(0)

# Construct small tensors for the function parameters
x = torch.randn(2, 4)  # batch size 2, dimension 4
mean = torch.randn(2, 4)  # same shape as x
log_sd = torch.randn(2, 4)  # log standard deviation, same shape as x

ARGS = {
    "x": x,
    "mean": mean,
    "log_sd": log_sd,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
gaussian_sample Ran
ran, honoured the contract we drafted
mdswyz/DiCMoR/trains/singleTask/model/glow.py
code served (permissive licence) · get_code("87324754644a55a3")
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 Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# Create small tensors for the gaussian_sample function
# eps: random noise tensor
eps = torch.randn(2, 4)

# mean: mean of the distribution
mean = torch.randn(2, 4)

# log_sd: log standard deviation
log_sd = torch.randn(2, 4)

ARGS = {
    'eps': eps,
    'mean': mean,
    'log_sd': log_sd
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
get_config_regression Ran
ran; our contract draft was wrong, not the code
mdswyz/DiCMoR/config.py
code served (permissive licence) · get_code("c02a56b7760c2b48")
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 EasyDict. 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 json
import os
import tempfile
from pathlib import Path
from easydict import EasyDict as edict

# Create a temporary config file with the structure expected by the function
config_data = {
    "model_name_1": {
        "commonParams": {
            "need_data_aligned": True,
            "param1": "value1"
        },
        "datasetParams": {
            "dataset_1": {
                "model_specific_param": "model_value"
            }
        }
    },
    "datasetCommonParams": {
        "dataset_root_dir": "/tmp/datasets",
        "dataset_1": {
            "aligned": {
                "featurePath": "features/aligned",
                "data_param": "data_value"
            },
            "unaligned": {
                "featurePath": "features/unaligned",
                "data_param": "data_value_unaligned"
            }
        }
    }
}

# Create a temporary directory and config file
temp_dir = tempfile.mkdtemp()
config_dir = Path(temp_dir) / 'config'
config_dir.mkdir(exist_ok=True)
config_file_path = config_dir / 'config_regression.json'

with open(config_file_path, 'w') as f:
    json.dump(config_data, f)

ARGS = {
    'model_name': 'model_name_1',
    'dataset_name': 'dataset_1',
    'config_file': str(config_file_path)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
easydict — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EasyDict — a EasyDict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a EasyDict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
MMDataLoader Not yet run
unverified (harvested, no recorded run)
mdswyz/DiCMoR/data_loader.py
code served (permissive licence) · get_code("a1286c4a93d7fe2f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 6 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 5 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.

FunctionAlso present inEarliest-datedOthers named
gaussian_log_p 5 other papers
3 dated earlier, 1 later, 1 same year, order not determinable · 1 only as an assembly brick
1807.03039 (2018-07)
Glow: Generative Flow with Invertible 1x1 Convolutions
1912.01219 (2019-12)
WaveFlow: A Compact Flow-based Model for Raw Audio
2206.05075 (2022-06)
Diffeomorphic Counterfactuals with Generative Models
and 2 more not named here
gaussian_sample 4 other papers
3 dated earlier, 1 same year, order not determinable
1807.03039 (2018-07)
Glow: Generative Flow with Invertible 1x1 Convolutions
1912.01219 (2019-12)
WaveFlow: A Compact Flow-based Model for Raw Audio
2206.05075 (2022-06)
Diffeomorphic Counterfactuals with Generative Models
and 1 more not named here
MMDataLoader 1 other paper
1 later
2412.12225 (2024-12)
DLF: Disentangled-Language-Focused Multimodal Sentiment Analysis
count_parameters 1 other paper
1 later
2412.12225 (2024-12)
DLF: Disentangled-Language-Focused Multimodal Sentiment Analysis
dict_to_str 1 other paper
1 later
2412.12225 (2024-12)
DLF: Disentangled-Language-Focused Multimodal Sentiment Analysis
get_config_regression 1 other paper
1 later
2412.12225 (2024-12)
DLF: Disentangled-Language-Focused Multimodal Sentiment Analysis

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

Recovering missing modality is popular in incomplete multimodal learning because it usually benefits downstream tasks. However, the existing methods often directly estimate missing modalities from the observed ones by deep neural networks, lacking consideration of the distribution gap between modalities, resulting in the inconsistency of distributions between the recovered and the true data. To mitigate this issue, in this work, we propose a novel recovery paradigm, Distribution-Consistent Modal Recovering (DiCMoR), to transfer the distributions from available modalities to missing modalities, which thus maintains the distribution consistency of recovered data. In particular, we design a class-specific flow based modality recovery method to transform cross-modal distributions on the condition of sample class, which could well predict a distributionconsistent space for missing modality by virtue of the invertibility and exact density estimation of normalizing flow. The generated data from the predicted distribution is integrated with available modalities for the task of classification. Experiments show that DiCMoR gains superior performances and is more robust than existing state-of-the-art methods under various missing patterns. Visualization results show that the distribution gaps between recovered modalities and missing modalities are mitigated. Codes are released at https://github.com/mdswyz/DiCMoR.

For agents

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

get_harvested_code_for_paper("Wang_Distribution-Consistent_Modal_Recovering_for_Incomplete_Multimodal_Learning_ICCV_2023_paper")
get_code_for_paper("Wang_Distribution-Consistent_Modal_Recovering_for_Incomplete_Multimodal_Learning_ICCV_2023_paper")
have("Wang_Distribution-Consistent_Modal_Recovering_for_Incomplete_Multimodal_Learning_ICCV_2023_paper")

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

curl https://syntology.ai/api/ran/Wang_Distribution-Consistent_Modal_Recovering_for_Incomplete_Multimodal_Learning_ICCV_2023_paper.json

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

[![Syntology run record](https://syntology.ai/api/ran/Wang_Distribution-Consistent_Modal_Recovering_for_Incomplete_Multimodal_Learning_ICCV_2023_paper.svg)](https://syntology.ai/paper/Wang_Distribution-Consistent_Modal_Recovering_for_Incomplete_Multimodal_Learning_ICCV_2023_paper)

Connect an agent — have() is free.