image_parser
image_parser appears in the code Syntology harvested for 19 papers, as 3 distinct code bodies found in 19 places (a place is one code body under one paper). At least one of them ran in 17 of the papers; 0 of the code bodies carry a behaviour fingerprint.
What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named image_parser do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.
Samples Syntology
Syntology ran 1 of the 3 distinct code bodies named image_parser; 2 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:
Licence is a property of each copy, so it is counted per place: 8 of the 19 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.
“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.
Papers
19 papers shown of 19, newest first; 19 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive; 3 papers have no page here and are shown by arXiv id only. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's code_sha256, Syntology's identity for that exact code: an agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.
| Paper | Date | File | Status Syntology | Licence |
|---|---|---|---|---|
| arXiv:2507.15504 | 2025-07 (from id) | PKU-YuanGroup/Video-LLaVA/videollava/eval/run_llava.py a7bee88c1c7fd6a3 |
ran · our draft was wrong | Apache-2.0 (permissive) |
| MIND: A Multi-agent Framework for Zero-shot Harmful Meme Detection | 9 Jul 2025 | destroy-lonely/MIND/utils/run_llava.py 449f2614cedc594b |
unverified | MIT (permissive) |
| LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token | 7 Jan 2025 | identical code first harvested elsewhere a7bee88c1c7fd6a3 |
ran · our draft was wrong | licence of this copy not recorded |
| LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering | 16 Dec 2024 | bibisbar/LLaVA-Steering/tinyllava/eval/run_tiny_llava.py a7bee88c1c7fd6a3 |
ran · our draft was wrong | Apache-2.0 (permissive) |
| Towards Low-Resource Harmful Meme Detection with LMM Agents | 8 Nov 2024 | jianzhao-huang/lorehm/utils/run_llava.py a7bee88c1c7fd6a3 |
ran · our draft was wrong | MIT (permissive) |
| Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving | 29 Oct 2024 | hustvl/senna/data_tools/senna_qa_utils.py a7bee88c1c7fd6a3 |
ran · our draft was wrong | Apache-2.0 (permissive) |
| LLaVA-KD: A Framework of Distilling Multimodal Large Language Models | 21 Oct 2024 | Fantasyele/LLaVA-KD/llavakd/eval/run_tiny_llava.py a7bee88c1c7fd6a3 |
ran · our draft was wrong | no licence file found · pointer only |
| Attention Prompting on Image for Large Vision-Language Models | 25 Sep 2024 | identical code first harvested elsewhere a7bee88c1c7fd6a3 |
ran · our draft was wrong | licence of this copy not recorded |
| ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation | 20 Sep 2024 | NVIDIA-AI-IOT/remembr/remembr/captioners/vila_captioner.py a7bee88c1c7fd6a3 |
ran · our draft was wrong | no licence file found · pointer only |
| LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation | 28 Aug 2024 | shufangxun/llava-mod/llavamod/eval/run_llava.py a7bee88c1c7fd6a3 |
ran · our draft was wrong | Apache-2.0 (permissive) |
| GalleryGPT: Analyzing Paintings with Large Multimodal Models | 1 Aug 2024 | steven640pixel/gallerygpt/llava/eval/run_llava.py a7bee88c1c7fd6a3 |
ran · our draft was wrong | Apache-2.0 (permissive) |
| EVALALIGN: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image Models | 24 Jun 2024 | identical code first harvested elsewhere a7bee88c1c7fd6a3 |
ran · our draft was wrong | licence of this copy not recorded |
| Enhancing Large Vision Language Models with Self-Training on Image Comprehension | 30 May 2024 | identical code first harvested elsewhere a7bee88c1c7fd6a3 |
ran · our draft was wrong | licence of this copy not recorded |
| Matryoshka Query Transformer for Large Vision-Language Models | 29 May 2024 | identical code first harvested elsewhere a7bee88c1c7fd6a3 |
ran · our draft was wrong | licence of this copy not recorded |
| Private Attribute Inference from Images with Vision-Language Models | 16 Apr 2024 | eth-sri/privacy-inference-multimodal/Experimentation/LLaVa-NeXT/run_llava.py a7bee88c1c7fd6a3 |
ran · our draft was wrong | MIT (permissive) |
| LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents | 9 Nov 2023 | identical code first harvested elsewhere a7bee88c1c7fd6a3 |
ran · our draft was wrong | licence of this copy not recorded |
| Visual Instruction Tuning | 17 Apr 2023 | ictnlp/LLaVA-Mini/llavamini/eval/run_llava_mini.py a7bee88c1c7fd6a3 |
ran · our draft was wrong | Apache-2.0 (permissive) |
| arXiv:2025.findings-acl.979 | Mrshenshen/FRUIT/models/caption.py 87e7eefadf4a0f7c |
unverified | Apache-2.0 (permissive) | |
| arXiv:2024.findings-emnlp.268 | HZQ950419/Math-LLaVA/llava/eval/run_llava.py a7bee88c1c7fd6a3 |
ran · our draft was wrong | Apache-2.0 (permissive) |
This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the harvest. "Pointer only" means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections