Arabic Sentence Segmentation Shared Task 2026

Arabic sentence segmentation datasets for the Arabic Sentence Segmentation Shared Task 2026

MediX-R1

Open Ended Medical Reinforcement Learning

OpenEarthAgent

The OpenEarthAgent Collection brings together the OpenEarthAgent model and its accompanying large-scale tool-augmented geospatial reasoning data.

Video-R2

VideoMathQA

VideoMathQA: Benchmarking Mathematical Reasoning via Multimodal Understanding in Videos

CASS

Large-scale dataset and model suite for cross-architecture GPU code transpilation between CUDA and HIP at both source and assembly levels

BiMediX2

BiMediX2 : Bio-Medical EXpert LMM for Diverse Medical Modalities

VideoGPT+

VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding

Video-ChatGPT

"Video-ChatGPT" is a video conversation model capable of generating meaningful conversation about videos.

PALO

PALO: A Polyglot Large Multimodal Model for 5B People

GeoChat

GeoChat is the first grounded Large Vision Language Model, specifically tailored to Remote Sensing(RS) scenarios.

Video-CoM

Video-CoM: Interactive Video Reasoning via Chain of Manipulations

DeepfakeJudge

A framework for deepfake detection and reasoning supervision at scale.

MedMO

Medical Foundation Model

FinMMEval Lab @CLEF'2026

Training datasets for FinMMEval Lab @CLEF'2026

NADI 2025 Sub-task 3 datasets

Official training and dev datasets for NADI 2025 Subtask 3 (Diacritic Restoration) Shared Task

GeoPixel

Pixel Grounding Large Multimodal Model in Remote Sensing

ArTST - Arabic Text Speech Transformer

Open source project for Arabic Speech Recognition and Generation

GLaMM

Grounding Large Multimodal Model (GLaMM), the first-of-its-kind model capable of generating natural language responses that are seamlessly integrated.

LLaVA++ (LLaMA-3 and Phi-3-Mini)

Extending Visual Capabilities of LLaVA with LLaMA-3 and Phi-3

MobiLlama

Collection of MobiLlama Language Models.

Satmae++

Collection of ViT models trained using SatMAE++ approach.