mbzuai-oryx / AINLinks
AIN - The First Arabic Inclusive Large Multimodal Model. It is a versatile bilingual LMM excelling in visual and contextual understanding across diverse domains.
☆47Updated 7 months ago
Alternatives and similar repositories for AIN
Users that are interested in AIN are comparing it to the libraries listed below
Sorting:
- [ACL 2025 🔥] A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding☆57Updated 5 months ago
- [NAACL 2025 🔥] CAMEL-Bench is an Arabic benchmark for evaluating multimodal models across eight domains with 29,000 questions.☆33Updated 6 months ago
- [EMNLP'23] ClimateGPT: a specialized LLM for conversations related to Climate Change and Sustainability topics in both English and Arabi…☆79Updated last year
- Bilingual Medical Mixture of Experts LLM☆31Updated 11 months ago
- Bio-Medical EXpert LMM with English and Arabic Language Capabilities☆71Updated 2 weeks ago
- [CVPR 2025 🔥] ALM-Bench is a multilingual multi-modal diverse cultural benchmark for 100 languages across 19 categories. It assesses the…☆45Updated 5 months ago
- vision language models finetuning notebooks & use cases (Medgemma - paligemma - florence .....)☆55Updated last month
- (WACV 2025 - Oral) Vision-language conversation in 10 languages including English, Chinese, French, Spanish, Russian, Japanese, Arabic, H…☆82Updated 3 months ago
- [BMVC 2025] Official Implementation of the paper "PerSense: Personalized Instance Segmentation in Dense Images"☆27Updated last month
- ☆48Updated last year
- Composition of Multimodal Language Models From Scratch☆15Updated last year
- ☆71Updated 4 months ago
- [ACL 2025 🔥] Time Travel is a Comprehensive Benchmark to Evaluate LMMs on Historical and Cultural Artifacts☆18Updated 5 months ago
- This repository contains the official source code for SALT: Parameter-Efficient Fine-Tuning via Singular Value Adaptation with Low-Rank T…☆27Updated 3 months ago
- VideoMathQA is a benchmark designed to evaluate mathematical reasoning in real-world educational videos☆17Updated 4 months ago
- [Fully open] [Encoder-free MLLM] Vision as LoRA☆342Updated 4 months ago
- Code, models, and data for "Advancements in Arabic Grammatical Error Detection and Correction: An Empirical Investigation". EMNLP 2023.☆17Updated last year
- ☆44Updated 4 months ago
- This is implementation of finetuning BLIP model for Visual Question Answering☆83Updated last year
- Official repository of paper titled "UniMed-CLIP: Towards a Unified Image-Text Pretraining Paradigm for Diverse Medical Imaging Modalitie…☆143Updated 6 months ago
- ☆38Updated 5 months ago
- ARB: A Comprehensive Arabic Multimodal Reasoning Benchmark☆17Updated 5 months ago
- Code for "Enhancing In-context Learning via Linear Probe Calibration"☆36Updated last year
- Florence-2 is a novel vision foundation model with a unified, prompt-based representation for a variety of computer vision and vision-lan…☆111Updated last year
- An open-source implementaion for fine-tuning SmolVLM.☆54Updated last month
- A minimal implementation of LLaVA-style VLM with interleaved image & text & video processing ability.☆96Updated 10 months ago
- Archive of Tasks and Results of the Video Browser Showdown☆13Updated 7 months ago
- Open-sourced code of miniGPT-Med☆136Updated last year
- ☆42Updated 2 years ago
- Knowledge Distillation using Contrastive Language-Image Pretraining (CLIP) without a teacher model.☆18Updated last year