SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.05926 · ECCV · 2024

BI-MDRG: Bridging Image History in Multimodal Dialogue Response Generation

Kang Zhang, Chang Yoo, Hee Yoon, Joshua Tian, Jin Tee, Eunseop Yoon, Du-Seong Chang, Yu-Jung Heo

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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, 1 violated it and 0 have no contract verdict; 3 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/2408.05926.json · badge: /api/ran/2408.05926.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
hee-suk-yoon/BI-MDRG canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
FeedForward Ran
ran; our contract draft was wrong, not the code
hee-suk-yoon/BI-MDRG/open_flamingo-main/open_flamingo/src/helpers.py
code served (permissive licence) · get_code("4d75570b4e91d0b4")
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) and returned Sequential. 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)

ARGS = {
    "dim": 64,
    "mult": 4
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
exists Ran
ran, violated the contract we drafted
hee-suk-yoon/BI-MDRG/open_flamingo-main/open_flamingo/src/helpers.py
pointer only (licence: MIT); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("aa5486a3650902d8")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ThomasMrY/VCT, and GitHub detected no licence in that repository 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.

getattr_recursive Ran
ran; our contract draft was wrong, not the code
hee-suk-yoon/BI-MDRG/open_flamingo-main/open_flamingo/src/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from sony/aki, is pointer only (licence: NOASSERTION) · get_code("fe68fff801021b23")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from sony/aki, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

postprocess_captioning_generation Ran
ran; our contract draft was wrong, not the code
hee-suk-yoon/BI-MDRG/open_flamingo-main/open_flamingo/eval/coco_metric.py
code served (permissive licence) · get_code("fc91265a186bcbd4")
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

torch.manual_seed(0)

# The function takes predictions as input and calls .split() on it
# This means predictions should be a string
# The function splits on 'Output' and takes the first part [0]

predictions = "This is a caption about something. Output some extra text that should be removed"

ARGS = {
    "predictions": predictions
}
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

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, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 3 the same month, 3 later) and 0 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
exists 486 other papers
371 dated earlier, 5 the same month, 99 later, 9 same year, order not determinable, 2 undated · 78 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1804.04637 (2018-04)
EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
and 483 more not named here
FeedForward 47 other papers
22 dated earlier, 1 the same month, 23 later, 1 same year, order not determinable · 4 only as an assembly brick
2204.14198 (2022-04)
Flamingo: a Visual Language Model for Few-Shot Learning
2308.02463 (2023-08)
Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&3D Medical Data
2308.06721 (2023-08)
IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models
and 44 more not named here
getattr_recursive 5 other papers
3 dated earlier, 1 the same month, 1 later · 1 only as an assembly brick
2308.02463 (2023-08)
Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&3D Medical Data
2310.00647 (2023-10)
Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learning
2402.10805 (2024-02)
Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond
and 2 more not named here
postprocess_captioning_generation 3 other papers
3 dated earlier
2310.00647 (2023-10)
Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learning
2403.10667 (2024-03)
Towards Unified Multi-Modal Personalization: Large Vision-Language Models for Generative Recommendation and Beyond
2406.08418 (2024-06)
OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text

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 Dialogue Response Generation (MDRG) is a recently proposed task where the model needs to generate responses in texts, images, or a blend of both based on the dialogue context. Due to the lack of a large-scale dataset specifically for this task and the benefits of leveraging powerful pre-trained models, previous work relies on the text modality as an intermediary step for both the image input and output of the model rather than adopting an end-to-end approach. However, this approach can overlook crucial information about the image, hindering 1) image-grounded text response and 2) consistency of objects in the image response. In this paper, we propose BI-MDRG that bridges the response generation path such that the image history information is utilized for enhanced relevance of text responses to the image content and the consistency of objects in sequential image responses. Through extensive experiments on the multimodal dialogue benchmark dataset, we show that BI-MDRG can effectively increase the quality of multimodal dialogue. Additionally, recognizing the gap in benchmark datasets for evaluating the image consistency in multimodal dialogue, we have created a curated set of 300 dialogues annotated to track object consistency across conversations. The code and the dataset is publicly available at https://github.com/hee-suk-yoon/BI-MDRG.

For agents

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

get_harvested_code_for_paper("2408.05926")
get_code_for_paper("2408.05926")
have("2408.05926")

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

curl https://syntology.ai/api/ran/2408.05926.json

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

[![Syntology run record](https://syntology.ai/api/ran/2408.05926.svg)](https://syntology.ai/paper/2408.05926)

Connect an agent — have() is free.