Stefano Ermon

In this engaging discussion, Stefano Ermon, a leading Professor of Computer Science at Stanford, reveals the inner workings of OpenAI's groundbreaking Sora model for AI-generated video. He discusses the shift from GANs to diffusion models and the significance of high-quality training data. The conversation explores the uncanny valley and how Sora's capabilities could reshape our understanding of video compression and generation. Ermon also hints at the exciting future of personalized video content and its applications in various fields.

Stefano Ermon, co-founder and CEO of Inception and former Stanford professor, explores diffusion language models and their potential to revolutionize AI. He explains how these models generate text in parallel, enhancing speed and cost efficiency compared to traditional methods. The discussion delves into the architecture's controllability and safety, the necessity of efficient inference for broader AI applications, and the exciting future of coding workflows and voice agents. Ermon emphasizes the role of these innovative models in shaping the next generation of generative intelligence.

Stefano Ermon, Stanford CS professor and founder of Inception Labs, explains Mercury — a diffusion approach that drafts full text then refines it. He discusses why diffusion can edit many tokens in parallel, how that reduces latency and GPU memory bottlenecks, which real-time applications benefit most, and the tradeoffs around quality, context length, and industry adoption.

Stefano Ermon, Stanford associate professor and CEO of Inception known for work on generative models, discusses adapting diffusion methods from images to text and code. He covers technical hurdles of discrete tokens, Mercury 2’s multi-token, low-latency inference, tradeoffs between denoising iterations and autoregressive sampling, real-world serving challenges, and where diffusion shines like editing and fast voice/agent loops.

Guests Arthur Mensch and Stefano Ermon discuss open foundation models and video models, emphasizing the importance of neutrality in technology and the regulation of AI applications. They explore the evolution of language models, the advantages of open-source collaboration, and the future prospects of specialized AI models. Additionally, they delve into the challenges and advancements in generating longer videos, showcasing how physics aids in accurate predictions and data compression in 3D models.