Intellectual hub of the topic
AI: Events
Technical context • Research
The PhotoRoom team verified which decisions in diffusion model training actually help and which can be simplified without losing quality.
AI: Events
Technical context • Development
We delve into the inner workings of the new MiniMax voice model, which can simultaneously understand speech, recognize the speaker, and generate a response.
The new version of Mistral's multimodal model can work with images, video, and text simultaneously, doing so quickly and accurately.
A model from Decart AI transforms video editing into a live process with no rendering or waiting. We break down how it works and why it's needed.
Tencent's new model allows users to edit and combine images using simple text instructions within the Yuanbao app.
Generative AI technology undeniably simplifies many aspects of life, yet questions regarding the safety and trustworthiness of generated content are emerging with increasing frequency.
AMD has introduced Nitro-AR, an autoregressive model that generates images faster than its diffusion counterparts and occupies less memory.
Overworld has released Waypoint-1, a video generation model that runs locally and responds to controls in real-time during the content creation process.
AI21 Labs explained why creating a model that simply does its job without surprises turned out to be harder than it seems.
Want to dive deeper into the world
of neuro-creativity?
Be the first to learn about new books, articles, and AI experiments
on our Telegram channel!