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

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.

To achieve the highest perceptual quality, state-of-the-art diffusion models are optimized with objectives that typically look very different from the maximum likelihood and the Evidence Lower Bound (...

We present CAT4D, a method for creating 4D (dynamic 3D) scenes from monocular video. CAT4D leverages a multi-view video diffusion model trained on a diverse combination of datasets to enable novel vie...

Designed to learn long-range interactions on sequential data, transformers continue to show state-of-the-art results on a wide variety of tasks. In contrast to CNNs, they contain no inductive bias tha...

A summary of my current thoughts on typicality, and its relevance to likelihood-based generative models.

A curated list for awesome discrete diffusion models resources. - kuleshov-group/awesome-discrete-diffusion-models

An overview of what I've been doing as part of my internship at Spotify in NYC this summer: using convolutional neural networks for audio-based music recommendation.