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.

Apr 23, 2026

Why Most Robot Demos Are Fake

Changan Chen, co-founder of Rhoda AI, discusses their vision-first approach to building foundation models for robotics. The conversation covers their unique training pipeline, the distinction between policy and world models, and the path to deploying data-efficient, reliable robots in real-world industrial settings.

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.

Nov 06, 2025

OpenAI Sora 2 Team: How Generative Video Will Unlock Creativity and World Models

The OpenAI Sora team discusses the technology behind their video generation model, from the diffusion transformers and space-time tokens that enable object permanence to their vision for Sora as a world simulator capable of scientific discovery. They also cover their product philosophy, which prioritizes creative inspiration over mindless consumption, and their strategy for building a new creator economy with IP holders.

Nov 05, 2025

OpenAI Sora 2 Team: How Generative Video Will Unlock Creativity and World Models

The OpenAI Sora team discusses the technology behind their video generation model, from the Diffusion Transformers and space-time tokens that enable object permanence to their vision for Sora as a world simulator for scientific discovery. They also cover the intentional product design of the Sora app, which optimizes for creative inspiration over mindless consumption, and their strategy for building a new creator economy with IP holders.

Oct 28, 2025

Google DeepMind Developers: How Nano Banana Was Made

Google DeepMind's Oliver Wang and Nicole Brichtova discuss the creation of the Nano Banana image model, its viral success driven by character consistency, and the future of AI in creative work, from user interfaces and 2D/3D world models to the next frontier of video generation and high-fidelity reasoning.