Ermon: Diffusion LLMs gain speed by modifying multiple tokens in parallel
Stefano Ermon · ⚡️Mercury: Ultra-Fast Diffusion LLMs — Estefano Ermon, CEO Inception Labs · Aug 4, 2025 · at 5:05
Stefano Ermon, Stanford professor and CEO of Inception Labs, explains how discrete diffusion language models achieve higher inference speeds than standard autoregressive models.
0:00 / 0:20exact quote · 20.6s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“That's kind of like the reason diffusion, diffusion language models are much faster compared to autoregressive models. Is that each neural network evaluation doesn't just give you one token, like in the typical autoregressive world, but it's able to Output, essentially, or modify multiple tokens. And so that's where you get the speed ups. The fact that you're able to modify many things basically in Paro.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Stefano Ermon
Ermon: Diffusion models could become the dominant architecture over autoregressive models
“I'm pretty optimistic about a future where diffusion models
Can become the dominant solution. I've seen it happen before with GANs a few years ago, so I wouldn't be surprised if that's the case also here.”
Ermon: Diffusion LLMs Pareto-dominate autoregressive models on inference efficiency
“On the inference side, what we're seeing is that diffusion models are much more efficient. We're actually able to Pareto dominate autoregressive models. If you think about the typical trade-off between throughput versus latency, which you kind of like cannot, …”
Inception generalist model matches Claude Haiku quality at 5-10x speed
“We had our generalist model evaluated by artificial analysis and the intelligence score from AA artificial analysis around 40. So it's comparable to GPT, 4.1 nano, cloud haiku, kind of like Close source speed optimized models. It's roughly comparable in terms …”
Ermon: Power constraints will drive diffusion models to replace frontier LLMs
“If it happens, it's gonna be driven by efficiency. Like we're all constrained by essentially power. And if you have, I mean, at the end of the day, it's all an inference game, right? Okay. Training is expensive, but then the thing that matters is being able to…”