ImageBind
ImageBind is a multimodal model from Meta AI (its Fundamental AI Research lab) that learns a single joint embedding space across six different modalities: images and video, text, audio, depth, thermal…
Explore Multimodal AI through related topics and the articles other pages reference most.
Articles that also belong to these categories. Counts cover all of Multimodal AI.
Showing 61-120 of 138 articles
ImageBind is a multimodal model from Meta AI (its Fundamental AI Research lab) that learns a single joint embedding space across six different modalities: images and video, text, audio, depth, thermal…
Intern-Decision is a family of three open-weight multimodal decision models (Intern-Decision-0.8B, Intern-Decision-2B and Intern-Decision-4B) released in late September 2026 by the InternLM team of Shanghai AI…
InternVL is a family of open-source multimodal large language models developed by the OpenGVLab research group at the Shanghai Artificial Intelligence Laboratory in collaboration with academic partners…
LFM3 is the third generation of Liquid Foundation Models (LFMs), a family of open-weight small language models and multimodal models released by Liquid AI on October 27, 2026.
LINGO-2 is a closed-loop vision-language-action model for autonomous driving developed by the British self-driving company Wayve.
LLaVA (Large Language and Vision Assistant) is an open-source family of multimodal large language models that connects a frozen vision encoder to a pre-trained large language model through a single learned…
LayoutLM is a family of pre-trained multimodal models developed by Microsoft Research for document AI, the task of automatically reading and understanding visually rich documents such as forms, invoices…
Llama 3.2 is a family of four open-weight large language models released by Meta on September 25, 2024, comprising lightweight 1 billion and 3 billion parameter text-only models for on-device AI and the 11…
Llama 3.2 Vision is the set of multimodal (image-plus-text) models in Meta's Llama 3.2 family, released on September 25, 2024 at the Meta Connect 2024 developer conference.
Llama 4 Scout and Llama 4 Maverick are open-weight, natively multimodal AI large language models developed by Meta and released on April 5, 2025.
LongCat-2.5 is a multimodal mixture-of-experts language model developed by Meituan for coding and long-running agent tasks.
MAGI-2 Preview is a public research release of a unified audio-video generation model developed by Sand.ai.
MM-BrowseComp is a benchmark for evaluating multimodal web-browsing AI agents, introduced in August 2025 by researchers from ByteDance, Nanjing University, M-A-P, the Institute of Automation of the Chinese…
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…
MMMU-Pro is a rigorous benchmark for evaluating multimodal AI systems on college-level, expert questions that genuinely require seeing an image, built as a harder and more robust version of the original MMMU…
MMStar (Multi-modal Star) is a vision-language model evaluation benchmark consisting of 1,500 multimodal samples that were filtered from six pre-existing benchmarks to ensure both visual dependency (questions…
Mage-VL-Cowork is a 4-billion-parameter computer-use agent model released by the Microsoft Mage Team at Microsoft on 30 October 2026.
MathVista is a benchmark for evaluating the mathematical reasoning capabilities of foundation models in visual contexts.
MetaCLIP (Metadata-Curated Language-Image Pre-training) is a data curation recipe and a family of vision-language models from Meta AI, introduced in the 2023 paper "Demystifying CLIP Data" by Hu Xu, Saining…
Ming-3.0 is a family of audio and speech models released by InclusionAI. Its official collection includes two audio-language models, a speech recognizer and two speech synthesizers.
MiniCPM-V is a family of open-weights multimodal large language models published by OpenBMB, the shared open-source brand of Tsinghua University's Natural Language Processing lab (THUNLP) and the Beijing…
Mistral Large 4 is a general-purpose multimodal model developed by Mistral AI. It entered public preview on October 6, 2026, with a mixture-of-experts architecture and API access.
Molmo is a family of open-weight, open-data vision-language models (VLMs) released by the Allen Institute for AI (Ai2) on 25 September 2024.
Muse Glimmer is an open-weight text-and-image model developed by Meta AI for local agent and coding workloads. Meta released the model on August 10, 2026 under the identifier meta-models/Muse-Glimmer-30B.
Muse Image is a proprietary image-generation and editing system developed by Meta Superintelligence Labs, a division of Meta.
Muse Spark is a multimodal reasoning model developed by Meta Superintelligence Labs (MSL), the artificial intelligence division Meta reorganized in 2025.
Muse Wonder is a series of multimodal reasoning models from Meta, released on October 12, 2026 for personal and professional AI agents.
The original NVIDIA Cosmos Reason release is an open, customizable, 7-billion-parameter reasoning vision-language model (VLM) for physical AI and robotics developed by Nvidia.
NVLM (short for NVIDIA Vision Language Model), released as NVLM 1.0, is a family of open multimodal large language models developed by Nvidia.
Nano Banana Pro is a professional grade image generation and editing model from Google DeepMind, released on November 20, 2025.
Nemotron 3.5 Bolt is an open-weight vision-language model released by NVIDIA on October 15, 2026 for local reasoning, coding, tool use, and browser and terminal tasks.
Nemotron 3.5 Super VL is an open-weight vision language model released by NVIDIA on October 15, 2026. It combines text, image, document, and video understanding with reasoning and tool use for agents.
PaLM-E (short for Pathways Language Model, Embodied) is an embodied multimodal large language model introduced by Google and TU Berlin in March 2023 that injects continuous sensor and image observations…
PaliGemma is an open vision-language model developed by Google that pairs the SigLIP image encoder with a Gemma language model, takes an image plus a text prompt as input, and produces text as output.
Paper2Video (full title: Paper2Video: Automatic Video Generation from Scientific Papers) is a research project from Show Lab at the National University of Singapore that formalizes and evaluates automatic…
Perception Encoder (PE) is a family of vision and vision-language encoders from Meta AI's Fundamental AI Research (FAIR) group, released in April 2025
Pika is an artificial intelligence video generation platform developed by Pika Labs (legal name Mellis, Inc.) that lets users create and edit short videos from text prompts, images, and existing clips, and it…
Pixtral is a family of multimodal vision-language models developed by Mistral AI, a French AI company founded in April 2023.
Project Astra is a research prototype from Google DeepMind that explores what a universal AI assistant might look like: a single agent that can see and hear the world in real time through a device camera and…
QvQ (styled QVQ) is a family of experimental visual reasoning models from the Qwen team at Alibaba.
Qwen-VL is the first family of open vision-language (multimodal) models from the Qwen team at Alibaba Cloud, able to take images, text, and bounding boxes as input and produce text and bounding boxes as output.
Qwen2-Audio is an audio-language model developed by the Qwen team at Alibaba Cloud, released in August 2024.
Qwen2-VL is a family of open-weight vision-language models released by the Qwen team at Alibaba Cloud between August and September 2024, in 2B, 7B, and 72B Instruct sizes.
Qwen2.5-VL is a series of open-weight vision-language models released on 26 January 2025 by the Qwen team at Alibaba (Alibaba Cloud), succeeding the earlier Qwen2-VL family.
Qwen3-Omni is a natively end-to-end omni-modal foundation model developed by the Qwen team at Alibaba Cloud, capable of understanding text, images, audio, and video and generating both text and natural speech…
Qwen3-VL is a family of open-weight vision-language models built by the Qwen team at Alibaba Cloud, first released in September 2025.
Qwen3.8-Flash-Next is an experimental open-weight multimodal large language model released by Alibaba Group's Qwen team on August 26, 2026.
Reka AI (commonly referred to as Reka) is an artificial intelligence research and product company founded in 2022 by former Google DeepMind, Google Brain, Meta FAIR, and Baidu researchers.
Reka Core is a frontier class multimodal foundation model developed by Reka AI, a research and product company founded in 2022 by former scientists from DeepMind, Google Brain, Meta FAIR, and Baidu.
Reka Edge is a 7-billion-parameter multimodal language model developed by Reka AI, introduced in April 2024 as the smallest member of the company's first publicly described model family.
Reka Flash is a family of multimodal large language models developed by Reka AI, a San Francisco Bay Area research company founded in 2022 by former researchers from Google DeepMind, Meta FAIR, and Google.
Robostral Navigate is an 8-billion-parameter vision language model developed by Mistral AI for instruction-following robot navigation.
SWE-bench Multimodal (also written SWE-bench M) is a benchmark that measures whether autonomous software-engineering systems can resolve bugs in visual
Seedream 4.0 is a unified image generation and editing model built by the Seed team at ByteDance.
SenseNova (Chinese: 日日新) is the family of foundation models developed by the Hong Kong-listed AI company SenseTime.
SigLIP (Sigmoid Loss for Language-Image Pre-training) is a family of vision-language encoders developed by researchers at Google DeepMind that pre-trains image and text encoders by treating each image-text…
Skywork-R1V (also written Skywork R1V) is a family of open-weight multimodal vision-language models built for chain-of-thought reasoning, developed by Skywork AI, the AGI and AIGC division of the Chinese…
SmolVLA (Small Vision-Language-Action) is a compact, open-source vision-language-action model (VLA) for robotics developed by Hugging Face and released in June 2025.
Sora 2 is a text-to-video and audio generation model developed by OpenAI, released on September 30, 2025, that OpenAI called "the GPT-3.5 moment for video." It succeeded the original Sora research preview from…
Starchild-1 is a real-time audio-video world model built by the AI lab Odyssey. It generates synchronized video and sound autoregressively, chunk by chunk, while a user streams new text, speech and action…