Skip to content
@mbzuai-oryx

ORYX

A Library for Large Vision-Language Models

Popular repositories Loading

  1. Awesome-LLM-Post-training Awesome-LLM-Post-training Public

    Awesome Reasoning LLM Tutorial/Survey/Guide

    Python 2.5k 169

  2. Video-ChatGPT Video-ChatGPT Public

    [ACL 2024 🔥] Video-ChatGPT is a video conversation model capable of generating meaningful conversation about videos. It combines the capabilities of LLMs with a pretrained visual encoder adapted fo…

    Python 1.5k 128

  3. groundingLMM groundingLMM Public

    [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.

    Python 967 56

  4. LLaVA-pp LLaVA-pp Public

    🔥🔥 LLaVA++: Extending LLaVA with Phi-3 and LLaMA-3 (LLaVA LLaMA-3, LLaVA Phi-3)

    Python 842 58

  5. GeoChat GeoChat Public

    [CVPR 2024 🔥] GeoChat, the first grounded Large Vision Language Model for Remote Sensing

    Python 752 67

  6. MobiLlama MobiLlama Public

    [ICLR-2025-SLLM Spotlight 🔥]MobiLlama : Small Language Model tailored for edge devices

    Python 672 50

Repositories

Showing 10 of 55 repositories
  • OmniEvalKit Public

    OmniEvalkit: A Unified Omni Evaluation Framework

    mbzuai-oryx/OmniEvalKit's past year of commit activity
    Python 10 0 0 0 Updated Sep 7, 2026
  • VideoGLaMM Public

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

    mbzuai-oryx/VideoGLaMM's past year of commit activity
    Python 105 4 9 0 Updated Sep 5, 2026
  • ALM-Bench Public

    [CVPR 2025 🔥] ALM-Bench is a multilingual multi-modal diverse cultural benchmark for 100 languages across 19 categories. It assesses the next generation of LMMs on cultural inclusitivity.

    mbzuai-oryx/ALM-Bench's past year of commit activity
    Python 47 3 1 0 Updated Sep 5, 2026
  • Video-ChatGPT Public

    [ACL 2024 🔥] Video-ChatGPT is a video conversation model capable of generating meaningful conversation about videos. It combines the capabilities of LLMs with a pretrained visual encoder adapted for spatiotemporal video representation. We also introduce a rigorous 'Quantitative Evaluation Benchmarking' for video-based conversational models.

    mbzuai-oryx/Video-ChatGPT's past year of commit activity
    Python 1,507 CC-BY-4.0 128 25 1 Updated Sep 5, 2026
  • VideoGPT-plus Public

    Official Repository of paper VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding

    mbzuai-oryx/VideoGPT-plus's past year of commit activity
    Python 293 CC-BY-4.0 19 16 0 Updated Sep 5, 2026
  • LLaVA-pp Public

    🔥🔥 LLaVA++: Extending LLaVA with Phi-3 and LLaMA-3 (LLaVA LLaMA-3, LLaVA Phi-3)

    mbzuai-oryx/LLaVA-pp's past year of commit activity
    Python 842 58 17 2 Updated Sep 5, 2026
  • groundingLMM Public

    [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.

    mbzuai-oryx/groundingLMM's past year of commit activity
    Python 967 Apache-2.0 56 35 1 Updated Sep 5, 2026
  • Video-LLaVA Public

    PG-Video-LLaVA: Pixel Grounding in Large Multimodal Video Models

    mbzuai-oryx/Video-LLaVA's past year of commit activity
    Python 263 12 15 0 Updated Sep 5, 2026
  • Video-R2 Public

    Video-R2: Reinforcing Consistent and Grounded Reasoning in Multimodal Language Models

    mbzuai-oryx/Video-R2's past year of commit activity
    Python 19 2 0 0 Updated Sep 5, 2026
  • VideoMathQA Public

    VideoMathQA is a benchmark designed to evaluate mathematical reasoning in real-world educational videos

    mbzuai-oryx/VideoMathQA's past year of commit activity
    25 1 1 0 Updated Sep 5, 2026
View all repositories