Multimodal AI

Forget AI models that feel stitched together. Alibaba's new Qwen3.5 Omni is a 'native' multimodal AI that was born to understand text, audio, and video seamlessly. Let's break down how this changes everything.

Forget complex HTML parsing. Let's build a web AI agent that navigates websites using only screenshots, just like a human. I'll walk you through setting up MolmoWeb-4B and see how it thinks, step-by-step.

Ever heard of an AI model that gets more powerful by shedding a third of its size? Meet Yuan 3.0 Ultra, a new model that's rewriting the rules on AI efficiency and performance. Let's break down how it works.

Ever wonder how AI could understand the world like we do? Meta's new PE-AV model is a huge step forward, learning to connect sights, sounds, and text in a single, unified brain. Let's break down how it works and why it's a big deal for the future of AI.

Google just dropped T5Gemma 2, a new family of open AI models that are smart, efficient, and can see. Let's break down what makes them tick, from their massive 128K context window to how they were built.

Ever wished you could magically remove a barking dog from a recording or lift a guitar solo from a noisy concert? Meta's new AI, SAM Audio, does just that, using simple text, visual, or time-based prompts to separate any sound from a mix.

Chinese AI startup Zhipu AI just dropped GLM-4.6V, an open-source vision model that's more than just a chatbot that can see. It can actually use visual tools, a huge step forward for multimodal AI.

Jina AI just dropped Jina-VLM, a surprisingly small 2.4B vision model that's a powerhouse in multilingual tasks. Let's break down how its clever design makes it so efficient without sacrificing performance.