Agentic video understanding
Agentic video understanding is an approach to video analysis in which a reasoning model chooses which parts of a video to inspect for a particular question.
Multimodal AI
Explore Multimodal AI through related topics and the articles other pages reference most.
Explore articles
Browse subtopics: Machine Learning
Articles that also belong to these categories. Counts cover all of Multimodal AI.
All articles (118)AI Models (45)Large Language Models (41)Open Source AI (28)Chinese AI (27)Google DeepMind (21)Computer Vision (18)AI Benchmarks (15)Generative AI (12)Meta AI (12)Embodied AI (10)Mixture of Experts (8)AI Agents (7)Machine Learning (7)Robotics (7)Google (6)Image Generation (6)Video Generation (5)Artificial Intelligence (4)OpenAI (4)AI Companies (3)AI Tools & Products (3)Reasoning Models (3)Small Language Models (3)AI Code Generation (2)AI Hardware (2)AI Research (2)Data & Datasets (2)Deep Learning (2)NVIDIA (2)Natural Language Processing (2)World Models (2)Anthropic (1)Autonomous Vehicles (1)Computer Science (1)Conversational AI (1)Diffusion Models (1)Information Retrieval (1)Model Architecture (1)Reinforcement Learning (1)Sensors (1)Speech & Audio AI (1)Transformer Models (1)
Showing 1-7 of 7 articles
CLIP (Contrastive Language-Image Pre-training)
CLIP, short for Contrastive Language-Image Pre-training, is a family of neural networks developed by OpenAI researchers to learn a shared representation of images and natural-language descriptions.
Claude Sonnet 4.5
Claude Sonnet 4.5 is a multimodal large language model (LLM) developed by Anthropic and released on September 29, 2025, which Anthropic described at launch as "the best coding model in the world." It is a…
Computer-use agent
A computer-use agent (CUA) is a category of AI agent in artificial intelligence that performs tasks by directly operating a general-purpose computer's graphical user interface (GUI) the way a human does, by…
Image-to-Text Models
Image-to-text models are machine learning systems that take an image as input and produce natural language text as output.
MMMU
MMMU (Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark) is a multimodal AI benchmark of 11,550 college-level questions that pairs text with images to test expert knowledge and…
data2vec
data2vec is a self-supervised learning framework from Meta AI (then Facebook AI Research) that applies the same training method to three different input types: speech, computer vision, and text.