Home › Code › find_closest_aspect_ratio

find_closest_aspect_ratio

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

find_closest_aspect_ratio appears in the code Syntology harvested for 45 papers, as 2 distinct code bodies found in 45 places (a place is one code body under one paper). At least one of them ran in 45 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 find_closest_aspect_ratio 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 2 of the 2 distinct code bodies named find_closest_aspect_ratio; 0 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

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

Licence is a property of each copy, so it is counted per place: 26 of the 45 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

45 papers shown of 45, newest first; 45 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; 5 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
Focus When Necessary: Adaptive Routing and Collaborative Grounding for Training-Free Visual Grounding added by Syntology 2026-06 (from id) TencentBAC/LazyMCoT/Internvl/utiles_internvl.py bd77f5f8067f18e9 ran · fixture could not drive it Apache-2.0 (permissive)
Closed-Form Spectral Regularization for Multi-Task Model Merging added by Syntology 2026-06 (from id) WalkerWorldPeace/MLLMerging/InternVL/internvl_chat/model_merging.py bd77f5f8067f18e9 ran · fixture could not drive it no licence file found · pointer only
VIABLE: A Visually Impaired Assistance Benchmark for VLM-as-a-Judge Evaluation added by Syntology 2026-05 (from id) YiyiyiZhao/VIABLE/viable/run_effectiveness/judge_infer_direct/utils_effectiveness/inference_internvl.py bd77f5f8067f18e9 ran · fixture could not drive it no licence file found · pointer only
When Do Diffusion Models Learn to Generate Multiple Objects? added by Syntology 2026-05 (from id) eugene6923/MOSAIC/mosaic/comfort_utils/model_utils/intern_vl.py bd77f5f8067f18e9 ran · fixture could not drive it no licence file found · pointer only
MLLM-4D: Towards Visual-based Spatial-Temporal Intelligence added by Syntology 2026-03 (from id) GVCLab/MLLM-4D/evaluation/model_inference/internvideo2_5.py bd77f5f8067f18e9 ran · fixture could not drive it no licence file found · pointer only
Enhancing the Outcome Reward-based RL Training of MLLMs with Self-Consistency Sampling added by Syntology 2025-11 (from id) GenuineWWD/SCS/evaluation/eval_internvl_m3cot.py bd77f5f8067f18e9 ran · fixture could not drive it Apache-2.0 (permissive)
LD-RPS: Zero-Shot Unified Image Restoration via Latent Diffusion Recurrent Posterior Sampling 1 Jul 2025 AMAP-ML/LD-RPS/get_prompts.py bd77f5f8067f18e9 ran · fixture could not drive it no licence file found · pointer only
MineAnyBuild: Benchmarking Spatial Planning for Open-world AI Agents 26 May 2025 identical code first harvested elsewhere bd77f5f8067f18e9 ran · fixture could not drive it licence of this copy not recorded
Unifying Multimodal Large Language Model Capabilities and Modalities via Model Merging 26 May 2025 identical code first harvested elsewhere bd77f5f8067f18e9 ran · fixture could not drive it licence of this copy not recorded
Decoupled Visual Interpretation and Linguistic Reasoning for Math Problem Solving 23 May 2025 identical code first harvested elsewhere bd77f5f8067f18e9 ran · fixture could not drive it licence of this copy not recorded
arXiv:2504.15485 2025-04 (from id) atinpothiraj/CAPTURe/occluded_scripts/intern.py bd77f5f8067f18e9 ran · fixture could not drive it MIT (permissive)
Pixel-SAIL: Single Transformer For Pixel-Grounded Understanding 14 Apr 2025 magic-research/Sa2VA/projects/sa2va/models/utils.py bd77f5f8067f18e9 ran · fixture could not drive it Apache-2.0 (permissive)
CoE: Chain-of-Explanation via Automatic Visual Concept Circuit Description and Polysemanticity Quantification 19 Mar 2025 YuWLong666/CoE/models/internvl.py bd77f5f8067f18e9 ran · fixture could not drive it BSD-3-Clause (permissive)
ViSpeak: Visual Instruction Feedback in Streaming Videos 17 Mar 2025 thunlp-mt/streamingbench/src/model/InternVL.py bd77f5f8067f18e9 ran · fixture could not drive it MIT (permissive)
Forgotten Polygons: Multimodal Large Language Models are Shape-Blind 21 Feb 2025 identical code first harvested elsewhere bd77f5f8067f18e9 ran · fixture could not drive it licence of this copy not recorded
CalibQuant: 1-Bit KV Cache Quantization for Multimodal LLMs 15 Feb 2025 identical code first harvested elsewhere bd77f5f8067f18e9 ran · fixture could not drive it licence of this copy not recorded
OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding? 9 Jan 2025 JoeLeelyf/OVO-Bench/models/InternVL2.py bd77f5f8067f18e9 ran · fixture could not drive it MIT (permissive)
Vinci: A Real-time Embodied Smart Assistant based on Egocentric Vision-Language Model 30 Dec 2024 identical code first harvested elsewhere bd77f5f8067f18e9 ran · fixture could not drive it licence of this copy not recorded
SPHERE: A Hierarchical Evaluation on Spatial Perception and Reasoning for Vision-Language Models 17 Dec 2024 zwenyu/SPHERE-VLM/models/vision_language_models/intern_vl2_5.py bd77f5f8067f18e9 ran · fixture could not drive it no licence file found · pointer only
Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity 9 Dec 2024 pipixin321/holmesvau/holmesvau/internvl_utils.py bd77f5f8067f18e9 ran · fixture could not drive it MIT (permissive)
LinVT: Empower Your Image-level Large Language Model to Understand Videos 6 Dec 2024 gls0425/linvt/streamlit_demo/model_worker.py bd77f5f8067f18e9 ran · fixture could not drive it no licence file found · pointer only
Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models 18 Nov 2024 gzcch/safety_snowball_agent/InternVL_assitant.py bd77f5f8067f18e9 ran · fixture could not drive it no licence file found · pointer only
Both Text and Images Leaked! A Systematic Analysis of Multimodal LLM Data Contamination 6 Nov 2024 MLLM-Data-Contamination/MM-Detect/mm_detect/mllms/internvl2.py bd77f5f8067f18e9 ran · fixture could not drive it Apache-2.0 (permissive)
R-CoT: Reverse Chain-of-Thought Problem Generation for Geometric Reasoning in Large Multimodal Models 23 Oct 2024 dle666/r-cot/GeoQA_test/model_vqa_rcot2b.py bd77f5f8067f18e9 ran · fixture could not drive it no licence file found · pointer only
Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference Under Ambiguities 22 Oct 2024 sled-group/COMFORT/comfort_utils/model_utils/intern_vl.py bd77f5f8067f18e9 ran · fixture could not drive it no licence file found · pointer only
MultiChartQA: Benchmarking Vision-Language Models on Multi-Chart Problems 18 Oct 2024 zivenzhu/multi-chart-qa/code/evaluate_internvl15.py bd77f5f8067f18e9 ran · fixture could not drive it no licence file found · pointer only
MMAD: The First-Ever Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection 12 Oct 2024 identical code first harvested elsewhere bd77f5f8067f18e9 ran · fixture could not drive it licence of this copy not recorded
Visual Perception in Text Strings 2 Oct 2024 JiaQiSJTU/VisionInText/src/evaluation_mm.py bd77f5f8067f18e9 ran · fixture could not drive it no licence file found · pointer only
Med-PMC: Medical Personalized Multi-modal Consultation with a Proactive Ask-First-Observe-Next Paradigm 16 Aug 2024 liuhc0428/med-pmc/src/models/InternVL.py bd77f5f8067f18e9 ran · fixture could not drive it no licence file found · pointer only
BIGbench: A Unified Benchmark for Evaluating Multi-dimensional Social Biases in Text-to-Image Models 21 Jul 2024 bigbench2024/bigbench2024/benchmark/internViT_pkg/internvl_detection.py d0487594e4d5c510 ran GPL-3.0 (copyleft) · pointer only
MMSci: A Dataset for Graduate-Level Multi-Discipline Multimodal Scientific Understanding 6 Jul 2024 leezekun/mmsci/mmsci-exps/model_loader.py bd77f5f8067f18e9 ran · fixture could not drive it no licence file found · pointer only
InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output 3 Jul 2024 identical code first harvested elsewhere bd77f5f8067f18e9 ran · fixture could not drive it licence of this copy not recorded
MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations 1 Jul 2024 mayubo2333/mmlongbench-doc/models/internvl_chat.py bd77f5f8067f18e9 ran · fixture could not drive it Apache-2.0 (permissive)
MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs 17 Jun 2024 liuziyu77/mmdu/model_generation/InternVL_chat_gen_ans.py bd77f5f8067f18e9 ran · fixture could not drive it Apache-2.0 (permissive)
DataComp-LM: In search of the next generation of training sets for language models 17 Jun 2024 jieyuz2/taskmeanything/tma/models/qa_model/imageqa_model.py bd77f5f8067f18e9 ran · fixture could not drive it Apache-2.0 (permissive)
Needle In A Multimodal Haystack 11 Jun 2024 OpenGVLab/MM-NIAH/eval_internvl.py bd77f5f8067f18e9 ran · fixture could not drive it no licence file found · pointer only
VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text 10 Jun 2024 tianyu-z/vcr/src/evaluation/utils.py bd77f5f8067f18e9 ran · fixture could not drive it CC-BY-SA-4.0 (copyleft) · pointer only
Unveiling the Tapestry of Consistency in Large Vision-Language Models 23 May 2024 foundation-multimodal-models/conbench/eval/InternVL-Chat-V1-5-26B.py bd77f5f8067f18e9 ran · fixture could not drive it Apache-2.0 (permissive)
IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models 23 Mar 2024 csebuetnlp/illusionvqa/inference_code/open_source/internvlm_inference.py bd77f5f8067f18e9 ran · fixture could not drive it no licence file found · pointer only
Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable 2D Repainting 20 Dec 2023 junwuzhang19/repaint123/main2.py bd77f5f8067f18e9 ran · fixture could not drive it MIT (permissive)
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter 2 Oct 2019 reycn/multi-modal-scale/script/3.evaluation.batch.py bd77f5f8067f18e9 ran · fixture could not drive it MIT (permissive)
arXiv:Zhang_Holmes-VAU_Towards_Long-term_Video_Anomaly_Understanding_at_Any_Granularity_CVPR_2025_paper pipixin321/HolmesVAU/holmesvau/internvl_utils.py bd77f5f8067f18e9 ran · fixture could not drive it MIT (permissive)
arXiv:Yang_PVC_Progressive_Visual_Token_Compression_for_Unified_Image_and_Video_CVPR_2025_paper OpenGVLab/PVC/utils/preprocess.py bd77f5f8067f18e9 ran · fixture could not drive it MIT (permissive)
arXiv:Guo_Integrating_Visual_Interpretation_and_Linguistic_Reasoning_for_Geometric_Problem_Solving_ICCV_2025_paper guozix/DVLR/eval/MathVerse/evaluation/generate_response_geo_text_qwen_2.py bd77f5f8067f18e9 ran · fixture could not drive it MIT (permissive)
arXiv:2025.acl-long.663 BlueZeros/ReflecTool/reflectool/models/InternVLChat.py bd77f5f8067f18e9 ran · fixture could not drive it 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