Jun 16, 2026

You Might Not Need 50 Diffusion Steps — Ziv Ilan, Nvidia

Ziv Ilan from NVIDIA details how latency in video diffusion models can be drastically reduced to achieve real-time generation. He presents a layered approach combining dynamic quantization for memory and speed, chunk-based caching to skip redundant denoising computations, and, most critically, step distillation—training models to achieve high-quality output in significantly fewer steps. These techniques, packaged in the open-source FastGen repository, offer additive performance gains, enabling real-time video on a single Blackwell B200 GPU.

May 26, 2026

Wavefunction Flows: Efficient Quantum Simulation of Continuous Flow Models

Continuous flow models map naturally to a Schrödinger equation, the fundamental equation of quantum mechanics. This discovery proves that a trained generative model can be efficiently simulated on a future quantum computer, enabling a new, more powerful type of access to its learned distribution for tasks like Monte Carlo estimation and structure discovery.

May 26, 2026

Where the Score Lives: What Wavelets Reveal About Diffusion Models

This talk explores the paradox of why diffusion models generalize rather than memorize. It introduces an analytically tractable, wavelet-based parameterization of the score function, allowing for an interpretable analysis of how architectural biases (like locality) and data statistics interact to influence denoising performance and generalization.

May 24, 2026

⚡️ Google's Open AI Strategy — Omar Sanseviero, Google DeepMind

An in-depth look at Gemma 4's novel transformer architecture with per-layer embeddings, enabling efficient parameter offloading for on-device inference. The discussion also covers its native multimodality, the state of fine-tuning, text-based diffusion models, and the growing intersection of research and engineering.

May 11, 2026

Predictive vs Generative AI: How They Work and When to Use Each

Predictive AI forecasts what will happen next based on historical data, while Generative AI creates new content by asking what something could look like. This summary explores their fundamental differences in outputs, data types, underlying models like transformers and diffusion systems, and how they can be used together in enterprise applications.

Apr 21, 2026

Building Generative Image & Video models at Scale - Sander Dieleman (Veo and Nano Banana)

Sander Dieleman from Google DeepMind provides a behind-the-scenes look at the key components of training large-scale diffusion models for audio-visual data. The talk covers the entire pipeline, from the critical role of data curation and latent representations to the mechanics of diffusion, network architectures, sampling with guidance, and advanced control signals.