Home › Code › load_image_from_base64

load_image_from_base64

Syntologyentry name in harvested coderead from the graph 2026-09-24

load_image_from_base64 appears in the code Syntology harvested for 87 papers, as 4 distinct code bodies found in 87 places (a place is one code body under one paper). At least one of them ran in 75 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 load_image_from_base64 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 3 of the 4 distinct code bodies named load_image_from_base64; 1 is unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

1ran · honoured contract
0ran · violated contract
0ran · our draft was wrong
0ran · fixture could not drive it
2ran
1unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 38 of the 87 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

87 papers shown of 87, newest first; 87 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, and the graph's for 6 papers added by Syntology; 7 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.

PaperDateFileStatus SyntologyLicence
OralAgent: Integrating Reasoning, Tools, and Knowledge for Interactive Dental Image Analysis added by Syntology 2026-05 (from id) isjinghao/OralAgent/oralagent/llava/mm_utils.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
CLIP Tricks You: Training-free Token Pruning for Efficient Pixel Grounding in Large Vision-Language Models added by Syntology 2026-05 (from id) sejong-rcv/LiteLVLM/model/llava/mm_utils.py 3aada9ef083faccd ran · honoured contract Apache-2.0 (permissive)
Uncertainty-Aware Knowledge Distillation for Multimodal Large Language Models added by Syntology 2026-03 (from id) Jingchensun/beta-kd/mobilevlm/utils.py 3aada9ef083faccd ran · honoured contract no licence file found · pointer only
Beyond Next-Token Alignment: Distilling Multimodal Large Language Models via Token Interactions added by Syntology 2026-02 (from id) lchen1019/Align-TI/alignti/mm_utils.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
Benchmarking Direct Preference Optimization for Medical Large Vision-Language Models added by Syntology 2026-01 (from id) dmis-lab/med-vlm-dpo/inference/LLaVA-Med/llava/mm_utils.py c3ee9d07c900dd55 ran no licence file found · pointer only
Uni-X: Mitigating Modality Conflict with a Two-End-Separated Architecture for Unified Multimodal Models added by Syntology 2025-09 (from id) CURRENTF/Uni-X/uni_arch/mm_utils.py c3ee9d07c900dd55 ran MIT (permissive)
arXiv:2507.18300 2025-07 (from id) 360CVGroup/LMM-Det/llava/mm_utils.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
arXiv:2507.04976 2025-07 (from id) EsYoon7/UVQA/llava/mm_utils.py c3ee9d07c900dd55 ran no licence file found · pointer only
Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details 19 Jun 2025 tencent/hunyuan3d-2/api_server.py 0dde2e782959c0bd unverified licence not identified · pointer only
Understand, Think, and Answer: Advancing Visual Reasoning with Large Multimodal Models 27 May 2025 jefferyzhan/griffon/griffon/mm_utils.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
SegEarth-R1: Geospatial Pixel Reasoning via Large Language Model 13 Apr 2025 earth-insights/segearth-r1/segearth_r1/mm_utils.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
EVEv2: Improved Baselines for Encoder-Free Vision-Language Models 10 Feb 2025 baaivision/EVE/EVEv1/eve/mm_utils.py 0dde2e782959c0bd unverified MIT (permissive)
MedRAX: Medical Reasoning Agent for Chest X-ray 4 Feb 2025 bowang-lab/medrax/medrax/llava/mm_utils.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding 22 Jan 2025 damo-nlp-sg/videollama3/videollama3/mm_utils.py 0dde2e782959c0bd unverified Apache-2.0 (permissive)
InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models 18 Dec 2024 congvvc/instructseg/instructseg/model/mipha/mm_utils.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
WiseAD: Knowledge Augmented End-to-End Autonomous Driving with Vision-Language Model 13 Dec 2024 wyddmw/WiseAD/mobilevlm/utils.py 3aada9ef083faccd ran · honoured contract no licence file found · pointer only
LinVT: Empower Your Image-level Large Language Model to Understand Videos 6 Dec 2024 gls0425/linvt/streamlit_demo/model_worker.py 0dde2e782959c0bd unverified no licence file found · pointer only
FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression 5 Dec 2024 codefanw/flashsloth/flashsloth/mm_utils.py c3ee9d07c900dd55 ran no licence file found · pointer only
LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos 29 Nov 2024 ttgeng233/LongVALE/longvalellm/mm_utils.py c3ee9d07c900dd55 ran MIT (permissive)
HyperSeg: Towards Universal Visual Segmentation with Large Language Model 26 Nov 2024 congvvc/HyperSeg/hyperseg/model/mipha/mm_utils.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks 23 Nov 2024 ASTRAL-Group/ASTRA/utility_eval/minigpt_mmbench.py 3aada9ef083faccd ran · honoured contract no licence file found · pointer only
V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimization 5 Nov 2024 yuxixie/v-dpo/llava_dpo/mm_utils.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI 15 Oct 2024 adacheng/egothink/models/lego/mm_utils.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality 7 Oct 2024 The-Martyr/CausalMM/llava-1.5/experiments/llava/mm_utils.py c3ee9d07c900dd55 ran MIT (permissive)
CDChat: A Large Multimodal Model for Remote Sensing Change Description 24 Sep 2024 techmn/cdchat/cdchat/mm_utils.py c3ee9d07c900dd55 ran no licence file found · pointer only
M$^2$PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning 24 Sep 2024 william-wang618/mmpt-emnlp2024/M2PT/mm_utils.py c3ee9d07c900dd55 ran no licence file found · pointer only
Fit and Prune: Fast and Training-free Visual Token Pruning for Multi-modal Large Language Models 16 Sep 2024 ywh187/fitprune/LLaVA_1.5/llava/mm_utils.py c3ee9d07c900dd55 ran no licence file found · pointer only
ChangeChat: An Interactive Model for Remote Sensing Change Analysis via Multimodal Instruction Tuning 13 Sep 2024 hanlinwu/changechat/changechat/mm_utils.py c3ee9d07c900dd55 ran no licence file found · pointer only
VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation 6 Sep 2024 mit-han-lab/vila-u/vila_u/mm_utils.py 0dde2e782959c0bd unverified MIT (permissive)
Recoverable Compression: A Multimodal Vision Token Recovery Mechanism Guided by Text Information 2 Sep 2024 banjiuyufen/Recoverable-Compression/llava/mm_utils.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
IAA: Inner-Adaptor Architecture Empowers Frozen Large Language Model with Multimodal Capabilities 23 Aug 2024 360cvgroup/inner-adaptor-architecture/iaa/mm_utils.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
ECG-Chat: A Large ECG-Language Model for Cardiac Disease Diagnosis 16 Aug 2024 YubaoZhao/ECG-Chat/llava/llava/mm_utils.py c3ee9d07c900dd55 ran no licence file found · pointer only
Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs 31 Jul 2024 hasanar1f/llava-hallunication-fix/modPAI/llava/mm_utils.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception 11 Jul 2024 baaivision/DenseFusion/densefusion/mm_utils.py 0dde2e782959c0bd unverified no licence file found · pointer only
Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs 28 Jun 2024 MBZUAI-LLM/web2code/web2code/llava/mm_utils.py c3ee9d07c900dd55 ran no licence file found · pointer only
Biomedical Visual Instruction Tuning with Clinician Preference Alignment 19 Jun 2024 mao1207/BioMed-VITAL/backbone/mm_utils.py c3ee9d07c900dd55 ran no licence file found · pointer only
Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM 18 Jun 2024 pipixin321/holmesvad/videollava/mm_utils.py c3ee9d07c900dd55 ran MIT (permissive)
mDPO: Conditional Preference Optimization for Multimodal Large Language Models 17 Jun 2024 luka-group/mDPO/bunny/bunny_utils/util/mm_utils.py 3aada9ef083faccd ran · honoured contract no licence file found · pointer only
DevBench: A multimodal developmental benchmark for language learning 14 Jun 2024 alvinwmtan/dev-bench/model_classes/modeling_tinyllava_phi.py c3ee9d07c900dd55 ran no licence file found · pointer only
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding 13 Jun 2024 mbzuai-oryx/videogpt-plus/videogpt_plus/mm_utils.py c3ee9d07c900dd55 ran CC-BY-4.0 · pointer only
Multimodal Table Understanding 12 Jun 2024 spursgozmy/table-llava/llava/mm_utils.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
3D-GRAND: A Million-Scale Dataset for 3D-LLMs with Better Grounding and Less Hallucination 7 Jun 2024 sled-group/3D-GRAND/demo/llava/mm_utils.py c3ee9d07c900dd55 ran no licence file found · pointer only
PosterLLaVa: Constructing a Unified Multi-modal Layout Generator with LLM 5 Jun 2024 posterllava/posterllava/llava/mm_utils.py c3ee9d07c900dd55 ran no licence file found · pointer only
Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare 29 May 2024 Q-Future/Compare2Score/q_align/mm_utils.py c3ee9d07c900dd55 ran MIT (permissive)
LOVA3: Learning to Visual Question Answering, Asking and Assessment 23 May 2024 showlab/LOVA3/llava/mm_utils.py c3ee9d07c900dd55 ran no licence file found · pointer only
Imp: Highly Capable Large Multimodal Models for Mobile Devices 20 May 2024 milvlg/imp/imp_llava/mm_utils.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
Automated Multi-level Preference for MLLMs 18 May 2024 takomc/amp/llava/mm_utils.py c3ee9d07c900dd55 ran no licence file found · pointer only
Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback 22 Apr 2024 Mr-Loevan/HSA-DPO/hsa_dpo/models/llava-v1_5/llava/mm_utils.py c3ee9d07c900dd55 ran no licence file found · pointer only
Self-Supervised Visual Preference Alignment 16 Apr 2024 Kevinz-code/SeVa/seva/llava/mm_utils.py c3ee9d07c900dd55 ran GPL-3.0 (copyleft) · pointer only
LaSagnA: Language-based Segmentation Assistant for Complex Queries 12 Apr 2024 congvvc/lasagna/model/llava/mm_utils.py 0dde2e782959c0bd unverified Apache-2.0 (permissive)
Unsolvable Problem Detection: Evaluating Trustworthiness of Vision Language Models 29 Mar 2024 atsumiyai/upd/vlms/cogvlm/cogvlm_vqa_updbench.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis 29 Mar 2024 opendatalab/h2rsvlm/vhm/mm_utils.py 0dde2e782959c0bd unverified Apache-2.0 (permissive)
Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models 27 Mar 2024 dvlab-research/minigemini/mgm/mm_utils.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model 21 Mar 2024 zamling/PSALM/psalm/mm_utils.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
Towards a clinically accessible radiology foundation model: open-access and lightweight, with automated evaluation 12 Mar 2024 microsoft/llava-rad/llava/mm_utils.py c3ee9d07c900dd55 ran no licence file found · pointer only
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios 7 Mar 2024 rikeilong/bay-cat/ADPO_CAT/mm_utils.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
ImgTrojan: Jailbreaking Vision-Language Models with ONE Image 5 Mar 2024 xijia-tao/imgtrojan/finetune/llava/mm_utils.py c3ee9d07c900dd55 ran no licence file found · pointer only
CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation 19 Feb 2024 xbmxb/coco-agent/llava/mm_utils.py c3ee9d07c900dd55 ran no licence file found · pointer only
ScreenAgent: A Vision Language Model-driven Computer Control Agent 9 Feb 2024 niuzaisheng/ScreenAgent/train/cogagent_model_worker.py 6493522dff8f8fa5 ran licence not identified · pointer only
MobileVLM V2: Faster and Stronger Baseline for Vision Language Model 6 Feb 2024 meituan-automl/mobilevlm/mobilevlm/utils.py 3aada9ef083faccd ran · honoured contract Apache-2.0 (permissive)
SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval 24 Jan 2024 wusiwei0410/scimmir/mm_utils.py c3ee9d07c900dd55 ran no licence file found · pointer only
Prometheus-Vision: Vision-Language Model as a Judge for Fine-Grained Evaluation 12 Jan 2024 kaistai/prometheus-vision/llava/mm_utils.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs 11 Jan 2024 tsb0601/MMVP/LLaVA/llava/mm_utils.py c3ee9d07c900dd55 ran no licence file found · pointer only
GroundingGPT:Language Enhanced Multi-modal Grounding Model 11 Jan 2024 lzw-lzw/groundinggpt/lego/mm_utils.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance 5 Jan 2024 pipilurj/mllm-protector/llava/mm_utils.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
LLaVA-Phi: Efficient Multi-Modal Assistant with Small Language Model 4 Jan 2024 zhuyiche/llava-phi/llava_phi/mm_utils.py c3ee9d07c900dd55 ran no licence file found · pointer only
LISA++: An Improved Baseline for Reasoning Segmentation with Large Language Model 28 Dec 2023 dvlab-research/lisa/model/llava/mm_utils.py 0dde2e782959c0bd unverified Apache-2.0 (permissive)
VCoder: Versatile Vision Encoders for Multimodal Large Language Models 21 Dec 2023 shi-labs/vcoder/vcoder_llava/mm_utils.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
GSVA: Generalized Segmentation via Multimodal Large Language Models 15 Dec 2023 leaplabthu/gsva/model/llava/mm_utils.py 0dde2e782959c0bd unverified Apache-2.0 (permissive)
Osprey: Pixel Understanding with Visual Instruction Tuning 15 Dec 2023 circleradon/osprey/osprey/mm_utils.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
Genixer: Empowering Multimodal Large Language Models as a Powerful Data Generator 11 Dec 2023 zhaohengyuan1/genixer/Genixer_LLaVA/llava/mm_utils.py c3ee9d07c900dd55 ran no licence file found · pointer only
Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos 7 Dec 2023 aldraus/quilt-llava/llava/mm_utils.py c3ee9d07c900dd55 ran MIT (permissive)
LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models 5 Dec 2023 ux-decoder/llava-grounding/llava/mm_utils.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
VTimeLLM: Empower LLM to Grasp Video Moments 30 Nov 2023 huangb23/vtimellm/vtimellm/mm_utils.py c3ee9d07c900dd55 ran no licence file found · pointer only
Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models 27 Nov 2023 aimagelab/safe-clip/LLaVA_generation/llava/mm_utils.py c3ee9d07c900dd55 ran no licence file found · pointer only
InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discovery 27 Nov 2023 idea-xl/instructmol/llava/mm_utils.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
GeoChat: Grounded Large Vision-Language Model for Remote Sensing 24 Nov 2023 mbzuai-oryx/geochat/geochat/mm_utils.py c3ee9d07c900dd55 ran no licence file found · pointer only
Qilin-Med-VL: Towards Chinese Large Vision-Language Model for General Healthcare 27 Oct 2023 williamliujl/qilin-med-vl/llava/mm_utils.py c3ee9d07c900dd55 ran no licence file found · pointer only
HallE-Control: Controlling Object Hallucination in Large Multimodal Models 3 Oct 2023 bronyayang/HallE_Switch/llava/mm_utils.py c3ee9d07c900dd55 ran no licence file found · pointer only
Sight Beyond Text: Multi-Modal Training Enhances LLMs in Truthfulness and Ethics 13 Sep 2023 ucsc-vlaa/sight-beyond-text/llava/mm_utils.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data 20 Aug 2023 icoz69/stablellava/llava/mm_utils.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
Self-attention Does Not Need $O(n^2)$ Memory 10 Dec 2021 X-iZhang/Libra/libra/mm_utils.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
arXiv:Xia_GSVA_Generalized_Segmentation_via_Multimodal_Large_Language_Models_CVPR_2024_paper LeapLabTHU/GSVA/model/llava/mm_utils.py 0dde2e782959c0bd unverified Apache-2.0 (permissive)
arXiv:2025.naacl-long.579 DAMO-NLP-SG/VideoLLaMA2/videollama2/mm_utils.py 0dde2e782959c0bd unverified Apache-2.0 (permissive)
arXiv:2024.findings-naacl.226 nguyennm1024/OSCaR/llava/mm_utils.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
arXiv:2024.findings-emnlp.775 YuxiXie/V-DPO/llava_dpo/mm_utils.py c3ee9d07c900dd55 ran Apache-2.0 (permissive)
arXiv:2024.findings-emnlp.268 HZQ950419/Math-LLaVA/llava/mm_utils.py c3ee9d07c900dd55 ran 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