SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2412.03561 · 2024

FLAIR: VLM with Fine-grained Language-informed Image Representations

arXiv · PDF · Open in the Atlas

Code that ran

13 of 20 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; 2 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 10 failures of our instrument; 7 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/2412.03561.json · badge: /api/ran/2412.03561.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
explainableml/flair canonical (classifier label)
classifier basis: census
13 ran · 6 no recorded run
ExplainableML/cosmos canonical (classifier label)
classifier basis: census
0 ran · 1 no recorded run
FunctionStatusWhere it lives
center_square_crop_box Ran
ran; our contract draft was wrong, not the code
explainableml/flair/src/visualization.py
pointer only (licence: NONE) · get_code("7c9f37f7273100f9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, explainableml/flair 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.

convert_to_custom_text_state_dict Ran
ran, violated the contract we drafted
explainableml/flair/src/flair/model.py
pointer only (licence: NONE); the stored copy get_code serves, from deep-real/dcp, is pointer only (licence: NONE) · get_code("f19962ebb134b3d7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, explainableml/flair 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.

draw_numbers Ran
ran, honoured the contract we drafted
explainableml/flair/src/flair/data.py
pointer only (licence: NONE) · get_code("7e7ffff6d9c929a3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, explainableml/flair 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_cast_dtype Ran
ran; our contract draft was wrong, not the code
explainableml/flair/src/flair/model.py
pointer only (licence: NONE) · get_code("dcd422d66b0581d8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, explainableml/flair 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_default_params Ran
ran; our contract draft was wrong, not the code
explainableml/flair/src/flair/params.py
pointer only (licence: NONE) · get_code("575ba28efe232215")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, explainableml/flair 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_input_dtype Ran
ran; our contract draft was wrong, not the code
explainableml/flair/src/flair/model.py
pointer only (licence: NONE); the stored copy get_code serves, from deep-real/dcp, is pointer only (licence: NONE) · get_code("b476c8cfbf0f1f47")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, explainableml/flair 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.

make_red_rgba_from_alpha Ran
ran, honoured the contract we drafted
explainableml/flair/src/visualization.py
pointer only (licence: NONE) · get_code("33cecaac74cf6257")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, explainableml/flair 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.

process_tar Ran
ran; our contract draft was wrong, not the code
explainableml/flair/preprocess/presplit_captions.py
pointer only (licence: NONE) · get_code("25977d0641f6f647")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, explainableml/flair 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.

random_sample_from_list Ran
ran; our contract draft was wrong, not the code
explainableml/flair/src/flair/data.py
pointer only (licence: NONE) · get_code("dae4304ab834bc31")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, explainableml/flair 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.

split_caption Ran
ran; our contract draft was wrong, not the code
explainableml/flair/src/flair/data.py
pointer only (licence: NONE) · get_code("7e3625da2fe10689")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, explainableml/flair 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.

split_caption Ran
ran; our contract draft was wrong, not the code
explainableml/flair/preprocess/presplit_captions.py
pointer only (licence: NONE) · get_code("23590b0021929371")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, explainableml/flair 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.

text_global_pool Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
explainableml/flair/src/flair/transformer.py
pointer only (licence: NONE) · get_code("61548bf76b531c76")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, explainableml/flair 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.

upsample_heatmap_to_size Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
explainableml/flair/src/visualization.py
pointer only (licence: NONE) · get_code("5aa6110f46cd2158")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, explainableml/flair 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.

download_weights_from_hf Not yet run
unverified (harvested, no recorded run)
explainableml/flair/src/flair/factory.py
pointer only (licence: NONE) · get_code("7ce5eede4639706f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, explainableml/flair 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.

gather_features Not yet run
unverified (harvested, no recorded run)
explainableml/flair/src/flair/loss.py
pointer only (licence: NONE); the stored copy get_code serves, from lxa9867/imagefolder, is pointer only (licence: NOASSERTION) · get_code("ddcbd45e940484ee")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, explainableml/flair 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.

get_model_config Not yet run
unverified (harvested, no recorded run)
explainableml/flair/src/flair/factory.py
pointer only (licence: NONE) · get_code("5c7cf820e99443ff")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, explainableml/flair 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.

neighbour_exchange Not yet run
unverified (harvested, no recorded run)
explainableml/flair/src/flair/loss.py
pointer only (licence: NONE); the stored copy get_code serves, from lxa9867/imagefolder, is pointer only (licence: NOASSERTION) · get_code("e332856e3c2fc814")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, explainableml/flair 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.

neighbour_exchange_bidir Not yet run
unverified (harvested, no recorded run)
explainableml/flair/src/flair/loss.py
pointer only (licence: NONE); the stored copy get_code serves, from lxa9867/imagefolder, is pointer only (licence: NOASSERTION) · get_code("5b1fd364afcf3c05")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, explainableml/flair 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.

parse_args Not yet run
unverified (harvested, no recorded run)
explainableml/flair/src/flair/params.py
pointer only (licence: NONE) · get_code("6932ab58022e237c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, explainableml/flair 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.

trigger_visualization_hook Not yet run
unverified (harvested, no recorded run)
ExplainableML/cosmos/src/seg_eval.py
pointer only (licence: NONE) · get_code("e22c0b4748cddefb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ExplainableML/cosmos 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 20 samples lifted from this paper's linked repositories, 20 carry a function identity and 0 do not. Of the 20 distinct functions with an identity, 9 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 4 the same month, 8 later) and 11 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
get_cast_dtype 66 other papers
55 dated earlier, 2 the same month, 8 later, 1 same year, order not determinable
2103.00020 (2021-03)
Learning Transferable Visual Models From Natural Language Supervision
2210.08402 (2022-10)
LAION-5B: An open large-scale dataset for training next generation image-text models
2212.07143 (2022-12)
Reproducible scaling laws for contrastive language-image learning
and 63 more not named here
gather_features 57 other papers
50 dated earlier, 1 the same month, 5 later, 1 same year, order not determinable · 1 only as an assembly brick
2206.01670 (2022-06)
Egocentric Video-Language Pretraining
2212.00638 (2022-12)
Finetune like you pretrain: Improved finetuning of zero-shot vision models
2301.07094 (2023-01)
Learning Customized Visual Models with Retrieval-Augmented Knowledge
and 54 more not named here
convert_to_custom_text_state_dict 49 other papers
43 dated earlier, 1 the same month, 4 later, 1 same year, order not determinable
2103.00020 (2021-03)
Learning Transferable Visual Models From Natural Language Supervision
2210.08402 (2022-10)
LAION-5B: An open large-scale dataset for training next generation image-text models
2212.07143 (2022-12)
Reproducible scaling laws for contrastive language-image learning
and 46 more not named here
get_input_dtype 29 other papers
24 dated earlier, 1 the same month, 4 later
2103.00020 (2021-03)
Learning Transferable Visual Models From Natural Language Supervision
2210.08402 (2022-10)
LAION-5B: An open large-scale dataset for training next generation image-text models
2212.07143 (2022-12)
Reproducible scaling laws for contrastive language-image learning
and 26 more not named here
get_model_config 22 other papers
19 dated earlier, 3 later
2211.07636 (2022-11)
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
2301.07094 (2023-01)
Learning Customized Visual Models with Retrieval-Augmented Knowledge
2303.14814 (2023-03)
WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation
and 19 more not named here
neighbour_exchange 19 other papers
16 dated earlier, 3 later
2303.15343 (2023-03)
Sigmoid Loss for Language Image Pre-Training
2403.15378 (2024-03)
Long-CLIP: Unlocking the Long-Text Capability of CLIP
2403.16831 (2024-03)
UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction
and 16 more not named here
neighbour_exchange_bidir 17 other papers
14 dated earlier, 3 later
2303.15343 (2023-03)
Sigmoid Loss for Language Image Pre-Training
2403.15378 (2024-03)
Long-CLIP: Unlocking the Long-Text Capability of CLIP
2403.16831 (2024-03)
UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction
and 14 more not named here
get_default_params 5 other papers
5 dated earlier
2308.05734 (2023-08)
AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining
2310.00108 (2023-10)
Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Study
2312.12856 (2023-12)
SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing
and 2 more not named here
text_global_pool 3 other papers
1 dated earlier, 2 later
2310.18341 (2023-10)
CXR-LLAVA: a multimodal large language model for interpreting chest X-ray images
Zhu_SkySense-O_Towards_Open-World_Remote_Sensing_Interpretation_with_Vision-Centric_Visual-Language_Modeling_CVPR_2025_paper (2025 (year only))
SkySense-O: Towards Open-World Remote Sensing Interpretation with Vision-Centric Visual-Language Modeling
2503.08048 (2025-03)
LongProLIP: A Probabilistic Vision-Language Model with Long Context 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

CLIP has shown impressive results in aligning images and texts at scale. However, its ability to capture detailed visual features remains limited because CLIP matches images and texts at a global level. To address this issue, we propose FLAIR, Fine-grained Language-informed Image Representations, an approach that utilizes long and detailed image descriptions to learn localized image embeddings. By sampling diverse sub-captions that describe fine-grained details about an image, we train our vision-language model to produce not only global embeddings but also text-specific image representations. Our model introduces text-conditioned attention pooling on top of local image tokens to produce fine-grained image representations that excel at retrieving detailed image content. We achieve state-of-the-art performance on both, existing multimodal retrieval benchmarks, as well as, our newly introduced fine-grained retrieval task which evaluates vision-language models' ability to retrieve partial image content. Furthermore, our experiments demonstrate the effectiveness of FLAIR trained on 30M image-text pairs in capturing fine-grained visual information, including zero-shot semantic segmentation, outperforming models trained on billions of pairs. Code is available at https://github.com/ExplainableML/flair .

For agents

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

get_harvested_code_for_paper("2412.03561")
get_code_for_paper("2412.03561")
have("2412.03561")

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

curl https://syntology.ai/api/ran/2412.03561.json

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

[![Syntology run record](https://syntology.ai/api/ran/2412.03561.svg)](https://syntology.ai/paper/2412.03561)

Connect an agent — have() is free.