unpad_image
unpad_image appears in the code Syntology harvested for 72 papers, as 8 distinct code bodies found in 73 places (a place is one code body under one paper). At least one of them ran in 69 of the papers; 5 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 unpad_image 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 5 of the 8 distinct code bodies named unpad_image; 3 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: 27 of the 73 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
72 papers shown of 72, newest first; 73 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 4 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.
| Paper | Date | File | Status Syntology | Licence |
|---|---|---|---|---|
| DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation added by Syntology | 2026-06 (from id) | SAI-Lab-NYU/DREAM-S/dream_s/model/modeling_llava_next.py 31c6472fe907e4f3 |
ran fingerprinted | no licence file found · pointer only |
| UHR-BAT: Budget-Aware Token Compression Vision-Language model for Ultra-High-Resolution Remote Sensing added by Syntology | 2026-04 (from id) | Yunkaidang/UHR/with-SAM/longva/longva/model/llava_arch.py 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| HiDrop: Hierarchical Vision Token Reduction in MLLMs via Late Injection, Concave Pyramid Pruning, and Early Exit added by Syntology | 2026-02 (from id) | EIT-NLP/HiDrop/llava/model/llava_arch.py 55c32993da87759b |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| VidLaDA: Bidirectional Diffusion Large Language Models for Efficient Video Understanding added by Syntology | 2026-01 (from id) | ziHoHe/VidLaDA/train/llava/model/llava_arch.py 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| Mitigating Object Hallucinations via Sentence-Level Early Intervention | 16 Jul 2025 | pspdada/SENTINEL/llava/model/llava_arch.py 55c32993da87759b |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| LLaVA-SP: Enhancing Visual Representation with Visual Spatial Tokens for MLLMs | 1 Jul 2025 | CnFaker/LLaVA-SP/llava/model/llava_arch.py 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| UniFork: Exploring Modality Alignment for Unified Multimodal Understanding and Generation | 20 Jun 2025 | tliby/unifork/unifork/model/llava_arch.py 55c32993da87759b |
ran · fixture could not drive it fingerprinted | no licence file found · pointer only |
| Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs | 12 Jun 2025 | theia-4869/cdpruner/llava/model/llava_arch.py 55c32993da87759b |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models | 25 May 2025 | identical code first harvested elsewhere 55c32993da87759b |
ran · fixture could not drive it fingerprinted | licence of this copy not recorded |
| VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation | 20 May 2025 | opengvlab/videochat-flash/llava-train_videochat/llava/model/llava_arch.py 2c7b71210b8a363f |
unverified | MIT (permissive) |
| Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling | 17 Apr 2025 | identical code first harvested elsewhere 55c32993da87759b |
ran · fixture could not drive it fingerprinted | licence of this copy not recorded |
| Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation | 3 Apr 2025 | identical code first harvested elsewhere 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | licence of this copy not recorded |
| ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement | 2 Apr 2025 | illume-unified-mllm/ILLUME_plus/ILLUME/illume/model/illume_arch.py 55c32993da87759b |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| Slow-Fast Architecture for Video Multi-Modal Large Language Models | 2 Apr 2025 | identical code first harvested elsewhere 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | licence of this copy not recorded |
| arXiv:2504.00502 | 2025-04 (from id) | icip-cas/ShortV/llava/model/llava_arch.py 55c32993da87759b |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model | 30 Mar 2025 | DriveVLA/OpenDriveVLA/llava/model/llava_arch.py 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| GraspCoT: Integrating Physical Property Reasoning for 6-DoF Grasping under Flexible Language Instructions | 20 Mar 2025 | cxmomo/GraspCoT/llava/model/llava_arch.py 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | MIT (permissive) |
| LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning | 19 Mar 2025 | identical code first harvested elsewhere 55c32993da87759b |
ran · fixture could not drive it fingerprinted | licence of this copy not recorded |
| Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing | 13 Mar 2025 | 1999Lyd/KVTP/llava/model/llava_arch.py 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | MIT (permissive) |
| QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video Comprehension | 11 Mar 2025 | identical code first harvested elsewhere 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | licence of this copy not recorded |
| VLAS: Vision-Language-Action Model With Speech Instructions For Customized Robot Manipulation | 2025-02 (from id) | identical code first harvested elsewhere 55c32993da87759b |
ran · fixture could not drive it fingerprinted | licence of this copy not recorded |
| Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Models | 20 Jan 2025 | identical code first harvested elsewhere 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | licence of this copy not recorded |
| LLaVA-UHD v2: an MLLM Integrating High-Resolution Feature Pyramid via Hierarchical Window Transformer | 18 Dec 2024 | thunlp/llava-uhd/llava/model/llava_arch.py 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| DriveMM: All-in-One Large Multimodal Model for Autonomous Driving | 10 Dec 2024 | zhijian11/DriveMM/llava/model/llava_arch.py 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| [CLS] Token Tells Everything Needed for Training-free Efficient MLLMs | 8 Dec 2024 | thu-mig/vtc-cls/llava/model/llava_arch.py 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay | 5 Dec 2024 | mcg-nju/p-mod/llava/model/llava_arch.py 55c32993da87759b |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning | 4 Dec 2024 | lavi-lab/aim/llava/model/llava_arch.py 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| Agri-LLaVA: Knowledge-Infused Large Multimodal Assistant on Agricultural Pests and Diseases | 3 Dec 2024 | kki2eve/agri-llava/agri_llava/model/llava_arch.py 55c32993da87759b |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs | 2 Dec 2024 | theia-4869/fastervlm/llava/model/llava_arch.py 55c32993da87759b |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification | 1 Dec 2024 | Osilly/dynamic_llava/llava/model/dynamic_llava_arch.py 55c32993da87759b |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models | 22 Nov 2024 | kd-tao/dycoke/llava/model/llava_arch.py 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models | 21 Nov 2024 | identical code first harvested elsewhere 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | licence of this copy not recorded |
| MC-LLaVA: Multi-Concept Personalized Vision-Language Model | 18 Nov 2024 | identical code first harvested elsewhere 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | licence of this copy not recorded |
| CCExpert: Advancing MLLM Capability in Remote Sensing Change Captioning with Difference-Aware Integration and a Foundational Dataset | 18 Nov 2024 | meize0729/ccexpert/llava/model/llava_arch.py 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model | 16 Nov 2024 | liuting20/mustdrop/llava/model/llava_arch.py 55c32993da87759b |
ran · fixture could not drive it fingerprinted | no licence file found · pointer only |
| Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters | 5 Nov 2024 | identical code first harvested elsewhere 55c32993da87759b |
ran · fixture could not drive it fingerprinted | licence of this copy not recorded |
| Right this way: Can VLMs Guide Us to See More to Answer Questions? | 1 Nov 2024 | identical code first harvested elsewhere 55c32993da87759b |
ran · fixture could not drive it fingerprinted | licence of this copy not recorded |
| Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving | 29 Oct 2024 | hustvl/senna/llava/senna/senna_llava_arch.py 55c32993da87759b |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding | 22 Oct 2024 | Vision-CAIR/LongVU/longvu/cambrian_arch.py 83d2977826140fdc |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction | 22 Oct 2024 | cooperx521/pyramiddrop/llava/model/llava_arch.py 55c32993da87759b |
ran · fixture could not drive it fingerprinted | MIT (permissive) |
| RAP: Retrieval-Augmented Personalization for Multimodal Large Language Models | 17 Oct 2024 | identical code first harvested elsewhere 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | licence of this copy not recorded |
| Reconstructive Visual Instruction Tuning | 12 Oct 2024 | haochen-wang409/ross/ross/model/ross_arch.py 55c32993da87759b |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| EMMA: Efficient Visual Alignment in Multi-Modal LLMs | 2 Oct 2024 | identical code first harvested elsewhere 55c32993da87759b |
ran · fixture could not drive it fingerprinted | licence of this copy not recorded |
| Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders | 28 Aug 2024 | identical code first harvested elsewhere 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | licence of this copy not recorded |
| HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models | 20 Aug 2024 | hasanar1f/hired/transformers/src/transformers/models/llava_next/modeling_llava_next.py f5183d69498ae311 |
ran · fixture could not drive it fingerprinted | MIT (permissive) |
| GalleryGPT: Analyzing Paintings with Large Multimodal Models | 1 Aug 2024 | steven640pixel/gallerygpt/llava/model/llava_arch.py 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models | 22 Jul 2024 | apple/ml-slowfast-llava/slowfast_llava/llava/model/llava_arch.py 55c32993da87759b |
ran · fixture could not drive it fingerprinted | no licence file found · pointer only |
| LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models | 10 Jul 2024 | identical code first harvested elsewhere 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | licence of this copy not recorded |
| Efficient Large Multi-modal Models via Visual Context Compression | 28 Jun 2024 | Beckschen/LLaVolta/llava/model/llava_arch.py 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs | 24 Jun 2024 | cambrian-mllm/cambrian/cambrian/model/cambrian_arch.py 83d2977826140fdc |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| EVALALIGN: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image Models | 24 Jun 2024 | sais-fuxi/evalalign/evalalign/model/llava_arch.py 55c32993da87759b |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| VoCo-LLaMA: Towards Vision Compression with Large Language Models | 18 Jun 2024 | identical code first harvested elsewhere 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | licence of this copy not recorded |
| ClawMachine: Learning to Fetch Visual Tokens for Referential Comprehension | 17 Jun 2024 | martian422/ClawMachine/ClawMachine/model/llava_arch.py 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | no licence file found · pointer only |
| Concept-skill Transferability-based Data Selection for Large Vision-Language Models | 16 Jun 2024 | g-jwlee/coincide_code/COINCIDE_cluster/tinyllava/model/llava_arch.py 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | no licence file found · pointer only |
| Beyond LLaVA-HD: Diving into High-Resolution Large Multimodal Models | 12 Jun 2024 | identical code first harvested elsewhere 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | licence of this copy not recorded |
| Parrot: Multilingual Visual Instruction Tuning | 4 Jun 2024 | AIDC-AI/Parrot/parrot/model/parrot_arch.py 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| Matryoshka Query Transformer for Large Vision-Language Models | 29 May 2024 | gordonhu608/mqt-llava/llava/model/llava_arch.py 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models | 24 May 2024 | alibaba/conv-llava/llava/model/llava_arch.py 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| FreeVA: Offline MLLM as Training-Free Video Assistant | 13 May 2024 | whwu95/freeva/llava/model/llava_arch.py 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| Boosting Multimodal Large Language Models with Visual Tokens Withdrawal for Rapid Inference | 9 May 2024 | lzhxmu/vtw/llava/model/llava_arch.py 55c32993da87759b |
ran · fixture could not drive it fingerprinted | no licence file found · pointer only |
| MoVA: Adapting Mixture of Vision Experts to Multimodal Context | 19 Apr 2024 | templex98/mova/mova/model/arch.py 55c32993da87759b |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| Unsupervised Universal Image Segmentation | 28 Dec 2023 | dantong88/llarva/llava/model/llava_arch.py 55c32993da87759b |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| Improved Baselines with Visual Instruction Tuning | 5 Oct 2023 | identical code first harvested elsewhere 55c32993da87759b |
ran · fixture could not drive it fingerprinted | licence of this copy not recorded |
| An Empirical Study of Scaling Instruct-Tuned Large Multimodal Models | 18 Sep 2023 | identical code first harvested elsewhere 55c32993da87759b |
ran · fixture could not drive it fingerprinted | licence of this copy not recorded |
| Visual Instruction Tuning | 17 Apr 2023 | haotian-liu/LLaVA/llava/model/llava_arch.py 55c32993da87759b |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| Visual Instruction Tuning | 17 Apr 2023 | LLaVA-VL/LLaVA-NeXT/llava/model/llava_arch.py 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) |
| Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data | 22 Jul 2021 | sberbank-ai/real-esrgan/RealESRGAN/utils.py ce655e9f8ddda6d8 |
unverified | BSD-3-Clause (permissive) |
| arXiv:Zhong_AIM_Adaptive_Inference_of_Multi-Modal_LLMs_via_Token_Merging_and_ICCV_2025_paper | LaVi-Lab/AIM/llava/model/llava_arch.py 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) | |
| arXiv:Zhang_Beyond_Training_Dynamic_Token_Merging_for_Zero-Shot_Video_Understanding_ICCV_2025_paper | Jam1ezhang/DYTO/dyto/llava/model/llava_arch.py 55c32993da87759b |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) | |
| arXiv:Xing_Conical_Visual_Concentration_for_Efficient_Large_Vision-Language_Models_CVPR_2025_paper | Cooperx521/PyramidDrop/llava/model/llava_arch.py 55c32993da87759b |
ran · fixture could not drive it fingerprinted | MIT (permissive) | |
| arXiv:2025.findings-acl.458 | DCDmllm/Align2LLaVA/reward_model/llava/model/llava_arch.py 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | Apache-2.0 (permissive) | |
| arXiv:2025.findings-acl.433 | haon-chen/mmE5/src/vlm_backbone/llava_next/modeling_llava_next.py 0f1f7661af2b16ac |
unverified | MIT (permissive) | |
| arXiv:2025.findings-acl.359 | G-JWLee/TAMP/llava/model/llava_arch.py 7606525af238fb64 |
ran · fixture could not drive it fingerprinted | 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