Search: “multimodal”

In this post, we'll explore how multimodal BioFMs work, showcase real-world applications in drug discovery and clinical development, and contextualize how AWS enables organizations to build and deploy

Z.ai: Z.ai releases GLM-5.3-Flash, the first natively multimodal GLM-5 series model, with 320B parameters, saying it outperforms GLM-5.2 at “one-tenth the price” — We introduce GLM-5.3-Flash, the firs

In this post, we build a multimodal retrieval system for aerospace manufacturing documents using Amazon Nova Multimodal Embeddings on Amazon Bedrock and Amazon S3 Vectors. We evaluate the system on 26

This Databricks resource discusses production-ready architectural approaches for integrating multimodal data (structured, unstructured, images, text, etc.) in healthcare AI systems. It likely covers b

This guide covers how to train and fine-tune multimodal embedding and reranker models using the Sentence Transformers library, enabling systems to work with both text and image data simultaneously. It

Brandon Vigliarolo / The Register: Cloudflare debuts open-weight multimodal decision models Clef and Clef-flash, claiming they are smarter and faster than Jev, based on Qwen3.8-27B and Qwen3.5-9B — Su

Rohail Saleem / Wccftech: Ox Alpha, a “stealth model” from an unknown AI lab with a 1M-token multimodal context and capacity for 100T tokens/day, goes viral after launching on OpenRouter — When an unk

Preference alignment has become a crucial component in enhancing the performance of Large Language Models (LLMs), yet its impact in Multimodal Large Language Models (MLLMs) remains comparatively under

The Sentence Transformers v5.4 update introduces first-class multimodal support, enabling the same familiar API to encode and compare texts, images, audio, and videos using both `SentenceTransforme...

Encode‑Prefill‑Decode (EPD) disaggregation is an inference optimization in NVIDIA Dynamo that separates vision encoding from LLM prefill–decode stages for multimodal requests. On image‑heavy prompts,

Gemma 4 12B is a unified, encoder-free multimodal model designed to bring high-performance intelligence to laptops and released under an Apache 2.0 license. It eliminates separate encoders by projecti

MiniMax-M3 is a large language model capable of handling 1 million token contexts and multimodal inputs while maintaining efficient inference performance. Together AI's blog post discusses techniques

This article discusses designing and implementing data pipelines capable of processing large-scale multimodal datasets (combining text, images, video, audio, etc.) using Ray, an open-source distribute

This Modal blog post describes a performance optimization technique for multimodal AI inference that achieves over 10% improvement through a simple Python dictionary-based approach. The article likely

NVIDIA's Nemotron 3 Nano Omni is a lightweight multimodal AI model capable of processing documents, audio, and video inputs for building intelligent agents. The model supports long-context understandi

NVIDIA Nemotron 3 Nano Omni is a 30B hybrid mixture-of-experts model that brings multimodal perception and reasoning into a single system, natively supporting text, image, video, and audio inputs whil

Learn how to deploy a multimodal WhatsApp ordering assistant that takes customer orders through text, voice notes, and real-time voice calls on a single business number, built on Amazon Bedrock AgentC

NVIDIA FLARE orchestrates federated multimodal AI training by supporting both full‑model and parameter‑efficient (adapter‑based) communication patterns, using large‑object externalization, tensor stre

Juro Osawa / The Information: Alibaba says its new open-source multimodal model, Qwen3.8-27B, passed 1M+ downloads within a few days of release, making it one of its fastest-growing models — Alibaba G

Mistral AI Blog: Mistral releases Shieldstral, a 3B multimodal safety classifier that it says matches models up to 7x its size on text safety, available under Apache 2.0 — Every product that ships a m

Kyt Dotson / SiliconANGLE: Singapore-based Ropedia, which captures real-world human experience via video and converts it into model-ready multimodal datasets, raised a 22M pre-Series A — Singapore-bas

Nemotron 3.5 Content Safety is NVIDIA's multimodal safety solution designed for enterprise AI applications, offering customizable safeguards for both text and image inputs across different global cont

Carl Franzen / VentureBeat: Alibaba releases Qwen3.7-Plus, a multimodal proprietary model with a 1M-token context window, costing $2 per 1M tokens, 60% less than text-only Qwen3.7-Max — However, like

Carl Franzen / VentureBeat: Google introduces Gemma 4 12B, a unified, encoder-free open multimodal model that can run locally on devices with 16GB of VRAM or unified memory — While many AI open source

True spatial intelligence for multimodal agents transcends low-level geometric perception, evolving from knowing where things are to understanding what they are for. While existing benchmarks, such as

Kyt Dotson / SiliconANGLE: Nvidia launches Nemotron 3 Nano Omni, an open multimodal model with a 30B-A3B hybrid MoE architecture; the Nemotron 3 family saw 50M+ downloads in the past year — Nvidia Cor

In this post, we show you how to build a video semantic search solution on Amazon Bedrock using Nova Multimodal Embeddings that intelligently understands user intent and retrieves accurate video resul

This paper was accepted at the Workshop on Navigating and Addressing Data Problems for Foundation Models (NADPFM) at ICLR 2026. Principled domain reweighting can substantially improve sample efficienc

We are expanding the Clef decision model family with Clef-omni, natively processing audio, video, images, and text in a single pipeline. We’ve also lowered Clef-flash pricing and boosted Clef inferenc

Condé Nast's editorial teams spent an average of 250 minutes per task searching a library of more than 140,000 videos using only titles and descriptions. Working with the AWS Generative AI Innovation

DeepSeek today debuted a new addition to its flagship V4 series of large language models. On launch, V4 Flash Vision Exp is only available via the Chinese startup’s paid developer platform. The compan

In this post, we walk through the problem space, our architecture on Amazon Bedrock and Amazon OpenSearch Serverless, the evaluation methodology we built on OpenStreetMap ground truth, four experiment

Step 3.7 Flash is a 198B-parameter Mixture-of-Experts vision-language model designed for enterprise-scale production workloads, featuring native image and video input, a 256k context window, and confi

Learn how to run SkyRL, an open-source reinforcement learning framework, on Amazon SageMaker HyperPod to post-train a Qwen3-VL-8B vision-language model with GRPO. This walkthrough covers building the

What is spatial reasoning? AI is moving beyond the digital world. The next generation of AI systems needs to understand and interact with physical environments, from robots to autonomous systems navig

If you’re building visual shopping, image or document understanding, or chart analysis, you need a way to verify whether your model’s response is actually grounded in the source image. A text-only eva

Auto-generated index of all models mentioned across the wiki.

Automated lint: 17 errors, 59669 warnings, 3 info

Auto-generated synthesis of 18054 entries about arxiv-cs-cv

Automated lint: 14 errors, 54840 warnings, 3 info

Automated lint: 12 errors, 54839 warnings, 3 info

Automated lint: 12 errors, 53990 warnings, 3 info

Traditional lakehouses were engineered for the era of reporting, not the high-velocity, multimodal demands of AI agents. To bridge this gap, architecture must evolve into an AI-native foundation — one

Automated lint: 19 errors, 64915 warnings, 3 info

Automated lint: 20 errors, 8743 warnings, 3 info

Want to know the latest from Google Cloud? Find it here in one handy location. Check back regularly for our newest updates, announcements, resources, events, learning opportunities, and more. Tip: Not