A deep dive on flow maps.

YouTube video by ML in PL

An exploration of N-dimensional rotary positional embeddings (RoPE) for vision transformers.

YouTube video by Bain Capital Ventures

[“Discover the harmony of AI and sound.”]

Latent representations for generative models.

YouTube video by Bain Capital Ventures

London, UK

YouTube video by Bain Capital Ventures

8 track album

Many classes of images exhibit rotational symmetry. Convolutional neural networks are sometimes trained using data augmentation to exploit this, but they are still required to learn the rotation equiv...

Deep neural networks (DNNs) trained for image denoising are able to generate high-quality samples with score-based reverse diffusion algorithms. These impressive capabilities seem to imply an escape f...

We’re rolling out a new, state-of-the-art video model, Veo 2, and updates to Imagen 3. Plus, check out our new experiment, Whisk.

Flow matching and diffusion models are two popular frameworks in generative modeling. Despite seeming similar, there is some confusion in the community about their exact connection. In this post, we a...