InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

  1. mlx-vlm

    AI repositories

    MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

    Indexed GitHub, Neywa-Labs 5,848 ★MITUpdated yesterday

    git clone https://github.com/Neywa-Labs/mlx-vlm.git
  2. This repo lists relevant papers summarized in our survey paper: A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models.

    Stale GitHub, JindongGu 511 ★Updated 20 months ago

    git clone https://github.com/JindongGu/Awesome-Prompting-on-Vision-Language-Model.git
  3. t2v_metrics

    AI repositories

    Evaluating text-to-image/video/3D models with VQAScore

    Stale GitHub, linzhiqiu 603 ★Apache-2.0Updated 5 months ago

    git clone https://github.com/linzhiqiu/t2v_metrics.git
  4. LLaVA-OneVision-2

    AI repositories

    Fully Open Framework for Democratized Multimodal Training

    Stale GitHub, EvolvingLMMs-Lab 1,232 ★Apache-2.0Updated 7 days ago

    git clone https://github.com/EvolvingLMMs-Lab/LLaVA-OneVision-2.git
  5. image text to text model by TaichuAI

    Indexed Hugging Face Hub, TaichuAI 3,044 ♥Updated 57 days ago

    TaichuAI/ZDTaichu5.0-9B
  6. MineContext

    AI repositories

    MineContext is your proactive context-aware AI partner(Context-Engineering+ChatGPT Pulse)

    Stale GitHub, volcengine 5,536 ★Apache-2.0Updated 6 months ago

    git clone https://github.com/volcengine/MineContext.git
  7. ocr

    Datasets & benchmarks

    Hugging Face dataset by uv-scripts

    Stale Hugging Face Hub, uv-scripts 166 ♥Updated 47 days ago

    uv-scripts/ocr
  8. InternVL

    AI repositories

    [CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

    Stale GitHub, OpenGVLab 10.2k ★MITUpdated 14 months ago

    git clone https://github.com/OpenGVLab/InternVL.git
  9. vidore-benchmark

    AI repositories

    Vision Document Retrieval (ViDoRe): Benchmark. Evaluation code for the ColPali paper.

    Stale GitHub, illuin-tech 278 ★MITUpdated 27 days ago

    git clone https://github.com/illuin-tech/vidore-benchmark.git
  10. ParseBench

    Datasets & benchmarks

    ParseBench - A Document Parsing Benchmark for AI Agents

    Indexed GitHub, run-llama 640 ★Apache-2.0Updated today

    git clone https://github.com/run-llama/ParseBench.git
  11. Mage-VL

    Models

    image text to text model by microsoft · transformers

    Stale Hugging Face Hub, microsoft 430 ♥apache-2.0Updated 3 months ago

    microsoft/Mage-VL
  12. HunyuanOCR

    Models

    image text to text model by tencent · transformers

    Stale Hugging Face Hub, tencent 834 ♥otherUpdated 2 months ago

    tencent/HunyuanOCR
  13. ReForm-Eval

    Datasets & benchmarks

    An benchmark for evaluating the capabilities of large vision-language models (LVLMs)

    Stale GitHub, FudanDISC 145 ★Apache-2.0Updated 3 years ago

    git clone https://github.com/FudanDISC/ReForm-Eval.git
  14. Dolphin

    Models

    image text to text model by ByteDance · transformers

    Stale Hugging Face Hub, ByteDance 519 ♥mitUpdated 16 months ago

    ByteDance/Dolphin
  15. roubao

    Agents & frameworks

    Android Automation Tool Based on Vision-Language Models

    Stale GitHub, Turbo1123 2,393 ★MITUpdated 10 months ago

    git clone https://github.com/Turbo1123/roubao.git
  16. VideoGLaMM

    Agents & frameworks

    [CVPR 2025 🔥]A Large Multimodal Model for Pixel-Level Visual Grounding in Videos

    Stale GitHub, mbzuai-oryx 106 ★Updated 2 months ago

    git clone https://github.com/mbzuai-oryx/VideoGLaMM.git
  17. groundingLMM

    Agents & frameworks

    [CVPR 2024 🔥] Grounding Large Multimodal Model (GLaMM), the first-of-its-kind model capable of generating natural language responses that are seamlessly integrated with object segmentation masks.

    Stale GitHub, mbzuai-oryx 969 ★Apache-2.0Updated 2 months ago

    git clone https://github.com/mbzuai-oryx/groundingLMM.git
  18. Xiaomi-OCR-0

    Models

    image text to text model by xiaomi-research · transformers

    Stale Hugging Face Hub, xiaomi-research 321 ♥apache-2.0Updated 18 days ago

    xiaomi-research/Xiaomi-OCR-0
  19. awesome-japanese-llm

    AI repositories

    日本語LLMまとめ - Overview of Japanese LLMs

    Stale GitHub, llm-jp 1,446 ★Apache-2.0Updated 7 days ago

    git clone https://github.com/llm-jp/awesome-japanese-llm.git
  20. CaPtain

    Agents & frameworks

    CaPtain: A Pipeline for Post-Training Code-as-Policy Robot Agents — CaPtain-Harness, SFT and RL training code, benchmark adapters

    Indexed GitHub, waltstephen 96 ★MITUpdated 6 days ago

    git clone https://github.com/waltstephen/CaPtain.git
  21. image text to text model by microsoft · transformers

    Indexed Hugging Face Hub, microsoft 225 ♥apache-2.0Updated 17 days ago

    microsoft/Mage-VL-Cowork
  22. NVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs.

    Indexed GitHub, NVIDIA-AI-Blueprints 1,986 ★Apache-2.0Updated today

    git clone https://github.com/NVIDIA-AI-Blueprints/video-search-and-summarization.git
  23. humanities_data_benchmark

    Datasets & benchmarks

    LLM Benchmark Suite for Humanities Data

    Stale GitHub, RISE-UNIBAS 32 ★GPL-3.0Updated 12 days ago

    git clone https://github.com/RISE-UNIBAS/humanities_data_benchmark.git
  24. NEWTON

    Agents & frameworks

    NEWTON: Agentic Planning for Physically Grounded Video Generation

    Stale GitHub, CUTEPKQ 139 ★MITUpdated 3 months ago

    git clone https://github.com/CUTEPKQ/NEWTON.git

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.