SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.08872 · 2024

xGen-MM (BLIP-3): A Family of Open Large Multimodal Models

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 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; 5 failures of our instrument; 1 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/2408.08872.json · badge: /api/ran/2408.08872.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
zzxslp/som-llava canonical (classifier label)
classifier basis: census
5 ran · 1 no recorded run
FunctionStatusWhere it lives
encode_image_from_file Ran
ran; our contract draft was wrong, not the code
zzxslp/som-llava/SoM/gpt4v.py
pointer only (licence: NONE) · get_code("cb9ab8a6655701f7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zzxslp/som-llava 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.

encode_image_from_pil Ran
ran; our contract draft was wrong, not the code
zzxslp/som-llava/SoM/gpt4v.py
pointer only (licence: NONE) · get_code("71138ba2dfbe50e1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zzxslp/som-llava 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.

ms_deform_attn_core_pytorch Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zzxslp/som-llava/SoM/ops/functions/ms_deform_attn_func.py
pointer only (licence: NONE) · get_code("c53ec291fabfc643")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zzxslp/som-llava 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.

prepare_inputs Ran
ran; our contract draft was wrong, not the code
zzxslp/som-llava/SoM/gpt4v.py
pointer only (licence: NONE) · get_code("de0b3299e81e5722")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zzxslp/som-llava 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.

remove_small_regions Ran
ran; our contract draft was wrong, not the code
zzxslp/som-llava/SoM/task_adapter/sam/tasks/inference_sam_m2m_auto.py
pointer only (licence: NONE) · get_code("f64fc4b6daa7513d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zzxslp/som-llava 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.

highlight Not yet run
unverified (harvested, no recorded run)
zzxslp/som-llava/SoM/demo_gpt4v_som.py
pointer only (licence: NONE) · get_code("bf3338796e883021")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zzxslp/som-llava 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 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 1 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
ms_deform_attn_core_pytorch 6 other papers
4 dated earlier, 1 later, 1 same year, order not determinable · 1 only as an assembly brick
2107.14467 (2021-07)
DPT: Deformable Patch-based Transformer for Visual Recognition
2111.14330 (2021-11)
Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsity
2203.01305 (2022-03)
DN-DETR: Accelerate DETR Training by Introducing Query DeNoising
and 3 more not named here
encode_image_from_file 1 other paper
1 dated earlier
2404.05580 (2024-04)
Responsible Visual Editing
encode_image_from_pil 1 other paper
1 dated earlier
2404.05580 (2024-04)
Responsible Visual Editing
highlight 1 other paper
1 dated earlier
2310.11441 (2023-10)
Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
remove_small_regions 1 other paper
1 dated earlier
2311.13601 (2023-11)
Visual In-Context Prompting

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 paper introduces BLIP-3, an open framework for developing Large Multimodal Models (LMMs). The framework comprises meticulously curated datasets, a training recipe, model architectures, and a resulting suite of LMMs. We release 4B and 14B models, including both the pre-trained base model and the instruction fine-tuned ones. Our models undergo rigorous evaluation across a range of tasks, including both single and multi-image benchmarks. Our models demonstrate competitive performance among open-source LMMs with similar model sizes. Our resulting LMMs demonstrate competitive performance among open-source LMMs with similar model sizes, with the ability to comprehend interleaved image-text inputs. Our training code, models, and all datasets used in this work, including the three largescale datasets we create and the preprocessed ones, will be open-sourced to better support the research community.

For agents

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

get_harvested_code_for_paper("2408.08872")
get_code_for_paper("2408.08872")
have("2408.08872")

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

curl https://syntology.ai/api/ran/2408.08872.json

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

[![Syntology run record](https://syntology.ai/api/ran/2408.08872.svg)](https://syntology.ai/paper/2408.08872)

Connect an agent — have() is free.