Tag

#multimodal AI

14 articles

Anthropic Releases Claude Opus 4.7: A Major Upgrade for Agentic Coding, High-Resolution Vision, and Long-Horizon Autonomous Tasks

Explore the advanced capabilities of Anthropic's Claude Opus 4.7, focusing on agentic coding, high-resolution vision, and long-horizon autonomous tasks. Understand how these features enable more sophisticated AI systems for real-world applications.

Apr 183

tools

MiniMax Releases MMX-CLI: A Command-Line Interface That Gives AI Agents Native Access to Image, Video, Speech, Music, Vision, and Search

MiniMax has released MMX-CLI, a Node.js-based command-line interface that provides native access to multimodal AI capabilities including image, video, speech, music, vision, and search for both developers and AI agents.

Apr 1222

Alibaba’s Tongyi Lab Releases VimRAG: a Multimodal RAG Framework that Uses a Memory Graph to Navigate Massive Visual Contexts

This explainer article introduces VimRAG, a new AI system from Alibaba that helps AI understand both text and images better using a memory graph. It explains how this technology works and why it matters for future AI applications.

Apr 1010

Alibaba Qwen Team Releases Qwen3.5 Omni: A Native Multimodal Model for Text, Audio, Video, and Realtime Interaction

Alibaba's Qwen team has released Qwen3.5 Omni, a native multimodal model capable of processing text, audio, video, and real-time interaction. Positioned as a competitor to Google's Gemini 3.1 Pro, the model marks a significant step forward in multimodal AI architecture.

Mar 3036

Google Releases Gemini 3.1 Flash Live: A Real-Time Multimodal Voice Model for Low-Latency Audio, Video, and Tool Use for AI Agents

Explore the advanced technical features of Google's Gemini 3.1 Flash Live, a real-time multimodal voice model designed for low-latency audio and video interactions.

Mar 2633

How to Build a Vision-Guided Web AI Agent with MolmoWeb-4B Using Multimodal Reasoning and Action Prediction

Researchers are exploring how to build vision-guided web AI agents using the MolmoWeb-4B model, which interprets screenshots to navigate and interact with websites without relying on HTML parsing.

Mar 2539

Automating complex finance workflows with multimodal AI

Finance leaders are leveraging multimodal AI to automate complex workflows, overcoming traditional document processing limitations. These advanced AI frameworks are transforming how financial institutions handle unstructured data.

Mar 2444

Mistral AI Releases Mistral Small 4: A 119B-Parameter MoE Model that Unifies Instruct, Reasoning, and Multimodal Workloads

Learn how Mistral AI's new Mistral Small 4 model unifies instruction following, reasoning, and multimodal capabilities into one powerful AI system using Mixture of Experts technology.

Mar 1652

Zhipu AI Introduces GLM-OCR: A 0.9B Multimodal OCR Model for Document Parsing and Key Information Extraction (KIE)

Learn how GLM-OCR, a new AI model from Zhipu AI, helps convert complex documents into digital data by reading text, understanding layout, and extracting key information.

Mar 1460

Google unifies text, image, video, and audio in a single vector space with Gemini Embedding 2

Google introduces Gemini Embedding 2, a multimodal embedding model that unifies text, images, video, audio, and documents into a single vector space, streamlining AI development and performance.

Mar 1161

OpenAI employees hint at a new omni model

OpenAI employees and leaked project details suggest the company is developing a new omni model, a multimodal AI system that could unify text, audio, and image processing.

Mar 960

LLM text data is drying up, but Meta points to unlabeled video as the next massive training frontier

This article explains how Meta and NYU researchers are exploring unlabeled video data as a new training frontier for multimodal AI models, challenging conventional assumptions about model architecture and data prioritization.

Mar 867