SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.05210 · EMNLP · 2024

Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality

Kaist, In Kweon, Junmo Kim, Jae Cho, Dong-Jin Kim, Youngtaek Oh

arXiv · PDF · Open in the Atlas

Code that ran

10 of 13 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, 1 violated it and 1 has no contract verdict; 7 failures of our instrument; 3 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/2410.05210.json · badge: /api/ran/2410.05210.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
ytaek-oh/fsc-clip marked official in Papers with Code
Papers with Code archive
10 ran · 3 no recorded run
FunctionStatusWhere it lives
ClipLoss Ran
ran on a synthesized input
ytaek-oh/fsc-clip/src/training/losses/loss.py
pointer only (licence: NOASSERTION) · get_code("f17a5e60ff546d38")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ytaek-oh/fsc-clip (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.

_clip_loss Ran
ran; our contract draft was wrong, not the code
ytaek-oh/fsc-clip/src/training/losses/loss.py
pointer only (licence: NOASSERTION) · get_code("e61334565bcaebfc")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ytaek-oh/fsc-clip (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.

_cosine_similarity Ran
ran, honoured the contract we drafted
ytaek-oh/fsc-clip/src/training/losses/loss.py
pointer only (licence: NOASSERTION) · get_code("a0b686002c0926a7")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ytaek-oh/fsc-clip (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.

_cross_entropy_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ytaek-oh/fsc-clip/src/training/losses/loss.py
pointer only (licence: NOASSERTION) · get_code("c3a11c639bee0bf1")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ytaek-oh/fsc-clip (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.

_cross_entropy_loss_with_nsr Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ytaek-oh/fsc-clip/src/training/losses/loss.py
pointer only (licence: NOASSERTION) · get_code("42a9cd65d6bb9511")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ytaek-oh/fsc-clip (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.

_focal_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ytaek-oh/fsc-clip/src/training/losses/loss.py
pointer only (licence: NOASSERTION) · get_code("4da9742a2716ca08")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ytaek-oh/fsc-clip (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.

_focal_loss_with_nsr Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ytaek-oh/fsc-clip/src/training/losses/loss.py
pointer only (licence: NOASSERTION) · get_code("eb0e8694e8e31b3f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ytaek-oh/fsc-clip (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.

_gather_features Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ytaek-oh/fsc-clip/src/training/losses/loss.py
pointer only (licence: NOASSERTION) · get_code("32f0e7829cc6c8cf")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ytaek-oh/fsc-clip (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.

build_neg_loss Ran
ran; our contract draft was wrong, not the code
ytaek-oh/fsc-clip/src/training/losses/loss.py
pointer only (licence: NOASSERTION) · get_code("0846465182b23ae5")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ytaek-oh/fsc-clip (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.

gather_features Ran
ran, violated the contract we drafted
ytaek-oh/fsc-clip/src/training/losses/loss.py
pointer only (licence: NOASSERTION) · get_code("b9b5c04cbd9445bc")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ytaek-oh/fsc-clip (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.

Global_HNLoss Not yet run
unverified (harvested, no recorded run)
ytaek-oh/fsc-clip/src/training/losses/loss.py
pointer only (licence: NOASSERTION) · get_code("b1b8efc2077fd92f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ytaek-oh/fsc-clip (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. No invocation recorded.

Local_HNLoss Not yet run
unverified (harvested, no recorded run)
ytaek-oh/fsc-clip/src/training/losses/loss.py
pointer only (licence: NOASSERTION) · get_code("6aaa0890842345c8")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ytaek-oh/fsc-clip (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. No invocation recorded.

LossFunction Not yet run
unverified (harvested, no recorded run)
ytaek-oh/fsc-clip/src/training/losses/loss.py
pointer only (licence: NOASSERTION) · get_code("f5395fcef01546fa")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ytaek-oh/fsc-clip (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. No invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 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 13 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

In this paper, we propose a new method to enhance compositional understanding in pretrained vision and language models (VLMs) without sacrificing performance in zero-shot multi-modal tasks. Traditional fine-tuning approaches often improve compositional reasoning at the cost of degrading multi-modal capabilities, primarily due to the use of global hard negative (HN) loss, which contrasts global representations of images and texts. This global HN loss pushes HN texts that are highly similar to the original ones, damaging the model's multi-modal representations. To overcome this limitation, we propose Fine-grained Selective Calibrated CLIP (FSC-CLIP), which integrates local hard negative loss and selective calibrated regularization. These innovations provide fine-grained negative supervision while preserving the model's representational integrity. Our extensive evaluations across diverse benchmarks for both compositionality and multi-modal tasks show that FSC-CLIP not only achieves compositionality on par with state-of-the-art models but also retains strong multi-modal capabilities. Code is available at: https://github.com/ytaek-oh/fsc-clip.

For agents

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

get_harvested_code_for_paper("2410.05210")
get_code_for_paper("2410.05210")
have("2410.05210")

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

curl https://syntology.ai/api/ran/2410.05210.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.05210.svg)](https://syntology.ai/paper/2410.05210)

Connect an agent — have() is free.