Home › Code › build_vision_projector

build_vision_projector

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

build_vision_projector appears in the code Syntology harvested for 23 papers, as 19 distinct code bodies found in 25 places (a place is one code body under one paper). At least one of them ran in 15 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 build_vision_projector 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 13 of the 19 distinct code bodies named build_vision_projector; 6 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
9ran · our draft was wrong
0ran · fixture could not drive it
4ran
6unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 11 of the 25 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

23 papers shown of 23, newest first; 25 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 2 papers added by Syntology; 1 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
VTaMo: Video-Text Alignment Model for Sign Language Translation added by Syntology 2026-07 (from id) junyi2005/vtamo/vtamo/mm_projector.py f7a5fc1ab99ecd55 ran licence not identified · pointer only
Uncertainty-Aware Knowledge Distillation for Multimodal Large Language Models added by Syntology 2026-03 (from id) Jingchensun/beta-kd/mobilevlm/model/vision_projector.py 0100980e0d43fee3 unverified no licence file found · pointer only
UniFork: Exploring Modality Alignment for Unified Multimodal Understanding and Generation 20 Jun 2025 tliby/unifork/unifork/model/projector.py d9010a83f7ea789c unverified no licence file found · pointer only
Causal-LLaVA: Causal Disentanglement for Mitigating Hallucination in Multimodal Large Language Models 26 May 2025 ignisavium/causal-llava/llava/model/multimodal_projector/builder.py 544bc3a3805f703a ran · our draft was wrong MIT (permissive)
Causal-LLaVA: Causal Disentanglement for Mitigating Hallucination in Multimodal Large Language Models 26 May 2025 ignisavium/causal-llava/confounders/get_projector_confounders.py 9d0bc30615da7d73 ran MIT (permissive)
AdCare-VLM: Leveraging Large Vision Language Model (LVLM) to Monitor Long-Term Medication Adherence and Care 1 May 2025 asad14053/AdCare-VLM/videollava/model/language_model/llava_llama.py ef4db0da176c674c ran · our draft was wrong MIT (permissive)
EgoLife: Towards Egocentric Life Assistant 5 Mar 2025 evolvinglmms-lab/egolife/EgoGPT/egogpt/model/language_model/egogpt_llama.py 6ac637835afcffbf ran · our draft was wrong licence not identified · pointer only
VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding 22 Jan 2025 damo-nlp-sg/videollama3/inference/transformers_api/modeling_videollama3.py 8409d5a94c95a154 unverified Apache-2.0 (permissive)
Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction 6 Jan 2025 Mark12Ding/Dispider/dispider/model/projectors.py 58a4a0132d489ed1 unverified Apache-2.0 (permissive)
GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-training 16 Dec 2024 alpha-innovator/geox/models/builder.py ef4db0da176c674c ran · our draft was wrong no licence file found · pointer only
WiseAD: Knowledge Augmented End-to-End Autonomous Driving with Vision-Language Model 13 Dec 2024 wyddmw/WiseAD/mobilevlm/model/vision_projector.py 0100980e0d43fee3 unverified no licence file found · pointer only
Frontiers in Intelligent Colonoscopy 22 Oct 2024 ai4colonoscopy/intelliscope/colongpt/model/multimodal_projector/builder.py 9f86dd0b9bd9a73e unverified Apache-2.0 (permissive)
TokenPacker: Efficient Visual Projector for Multimodal LLM 2 Jul 2024 circleradon/tokenpacker/llava/model/multimodal_projector/builder.py 65b5e7ce2771cc06 ran · our draft was wrong no licence file found · pointer only
STLLaVA-Med: Self-Training Large Language and Vision Assistant for Medical Question-Answering 28 Jun 2024 heliossun/STLLaVA-Med/llava/model/language_model/llava_llama.py fba2ee2fd7519dce ran · our draft was wrong MIT (permissive)
TroL: Traversal of Layers for Large Language and Vision Models 18 Jun 2024 ByungKwanLee/TroL/trol/arch_internlm2/modeling_trol.py 4836c910f4ac2e06 ran · our draft was wrong no licence file found · pointer only
TroL: Traversal of Layers for Large Language and Vision Models 18 Jun 2024 byungkwanlee/trol/trol/arch_internlm2/build_module.py ec01154f26b3b92e ran no licence file found · pointer only
mDPO: Conditional Preference Optimization for Multimodal Large Language Models 17 Jun 2024 luka-group/mDPO/bunny/modeling_bunny_phi.py a42bf90646a3347f ran no licence file found · pointer only
Parrot: Multilingual Visual Instruction Tuning 4 Jun 2024 AIDC-AI/Parrot/parrot/model/multimodal_projector/builder.py ef4db0da176c674c ran · our draft was wrong Apache-2.0 (permissive)
Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts 18 May 2024 hitsz-tmg/umoe-scaling-unified-multimodal-llms/Uni_MoE/Uni_MoE_audio/model/multimodal_projector/builder.py ef4db0da176c674c ran · our draft was wrong no licence file found · pointer only
LLaVA-Gemma: Accelerating Multimodal Foundation Models with a Compact Language Model 29 Mar 2024 intellabs/multimodal_cognitive_ai/LLaVA-Gemma/llava/model/multimodal_projector/builder.py ef4db0da176c674c ran · our draft was wrong MIT (permissive)
Yi: Open Foundation Models by 01.AI 7 Mar 2024 01-ai/yi/VL/llava/model/llava_llama.py 9fa178e6891384f1 ran · our draft was wrong Apache-2.0 (permissive)
MobileVLM V2: Faster and Stronger Baseline for Vision Language Model 6 Feb 2024 meituan-automl/mobilevlm/mobilevlm/model/vision_projector.py 0100980e0d43fee3 unverified Apache-2.0 (permissive)
Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding 5 Jun 2023 damo-nlp-sg/videollama2/videollama2/model/videollama2_arch.py 7aa936fbe4f3d6fe ran · our draft was wrong Apache-2.0 (permissive)
Visual Instruction Tuning 17 Apr 2023 dinhvietcuong1996/icme25-inova/llava/model/language_model/llava_llama.py ea7ba84c548c5a33 ran · our draft was wrong Apache-2.0 (permissive)
arXiv:2025.naacl-long.579 DAMO-NLP-SG/VideoLLaMA2/videollama2/model/projector.py b52010a2b2ad8f78 unverified 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