MechanismVideo · 4:24 — 5:08

The real-to-sim-to-real pipeline maps real environments into aligned digital worlds to replace costly real-world data collection with scalable simulation data for robotics training and evaluation.

Yunzhu Li explains the Synix approach: reconstruct real environments in simulation with precise alignment, then use the simulation to generate training and evaluation data at scale, bypassing bottlenecks in robotics development. ✦ AI generated

Yunzhu Li · a16z Podcast · 2026-07-28 · original ↗

Share card ↓Export .md Export .txt

starts at this moment · 4:24

Elicited by

“Provide everyone with a quick overview of your background and what Scenix does.”

As we are developing what we call a real to sim to real pipeline. We want to map the real environments into the digital world that has the best alignments with the real environments. By alignments we mean that whatever happens in the digital world is also going to happen in the real environments such that we can replace all the data, all the evaluation we need in the real environment by using the data that can generate at a scalable way in our digital world.

verbatim transcript · starts at 4:24

Transcript · around this moment

4:18real physical environments. >> So for cynics the unique opportunity we see is that there has been a lot of like a bottlenecks. Right now we see faced by the developments of general purpose robots especially around training and also around evaluations. So as we are developing what we call a real to sim to real pipeline. Okay. We want to map the real environments into the digital world that has the best alignments with the

4:44real environments. By alignments we mean that whatever happens in the digital world is also going to happen in the real environments >> such that we can replace all the data all the evaluation we need in the real environment by using the data that can generate at a scalable way in our digital world. So that is how everything started in Synex. We put together a very very strong and best teams around

5:08robotics, robot learning and also simulation and rendering trying to build this realtom real stack to solve some of the key bottlenecks. >> It's amazing that you two work together. >> Yeah. And uh there is a funny story here because you would think because we worked together he was my amazing postto we've been talking about this and world lab um um integration for a long time. It's actually not true. They came into

5:33World Wars as a customer. >> Really? >> When we when we released the first version of our generative model called Marble last winter around uh November, December, >> Cynics just signed up. >> No kidding. AS A CUSTOMER. >> YES. And I didn't even know what it was. And then I realized this is Vindrew's company. I called Vindro. I'm like, "Wow, this is your company." and you guys and and then we realized there's so

▦ Synix ◉ Yunzhu Li

Around this claim

Evidence · 3

The unique bottleneck in general-purpose robotics is the lack of data for training and evaluation, which can be solved by a 'real-to-sim-to-real' pipeline that aligns digital worlds with physical environments so that simulation data replaces real-world data at scale.Yunzhu Li · a16z Podcast · conf 100%Mapping real environments into aligned digital worlds enables replacing all real-world robotics data with scalable digital data, solving the key training and evaluation bottlenecks in general-purpose robotics.Yinuo · a16z Podcast · conf 95%Scene simulation provides reliability and efficiency that real-world data cannot, by enabling systematic randomization and coverage of the state space for robust robot training, and by allowing faster-than-human training speeds.Yunu Guo · a16z Podcast · conf 85%

Extends · 2

Simulation provides two unique benefits that real-world data cannot: systematic coverage for reliability (controllable variation of all state-space parameters) and accelerated data generation for efficiency (faster-than-real-time training).Yunzhu Li · a16z Podcast · conf 90%The role simulation plays that real-world data cannot is counterfactual reasoning—playing out events that haven't happened or cannot happen—and this is critical for robotics because we cannot possibly have enough real-world data.Fei-Fei Li · a16z Podcast · conf 80%

This moment responds to

provides context → The next frontier of AI is spatial intelligence — creating AI that can generate, understand, reason with, and interact with physical or virtual spaces.Fei-Fei Li · a16z Podcast extends → Simulation is not an alternative to real-world data but plays a critical complementary role that real data cannot fill: counterfactual reasoning — playing out events that haven't happened, cannot happen, or lack sufficient real-world data.Fei-Fei Li · a16z Podcast