00:07:48 · Jim Fan
We are starting to solve the world a bit using modern LLMs and also reinforcement learning, but this time, it's not from scratch. Right? It's aural reasoning on top of LLM, then we have things like computer using agents, MCPs that can use tools. We're finally starting to solve that. So even though we didn't... We were not able to completely solve in 2016, but I think that summer's internship really shaped my research taste, which is that, you know, the data pipeline can be very complex, but a model interface needs to be very simple because only simple and elegant methods can leverage all kinds of the data sources. Only the simple methods can scale the best with compute. Right? It's really a perspective on how to approach these hard problems. So that was the summer. And then I started my PhD with Professor Fei Fei Li at Stanford, and as everyone knows, Fei Fei doesn't need an intro. She's the world renowned scientist on computer vision. She was known for ImageNet, and at that time, computer vision was about image segmentation, benchmarks, classification, video video annotation, and so on. And we call those static computer vision. You have a data set, you have static images and videos, and you map that to some sort of labels. Now Fei Fei's vision was that static computer vision is hitting a wall, and the next big revolution would be embodied vision, meaning that computer vision should be solved with agency. So you can have visual agents in simulation and in the real world, and the visual agents in the real world is basically robotics. So from 2016 to 2021, over the five years I was at the lab, I basically witnessed Fei Fei's lab's transition from static to in body vision and then to have a new north star of solving these kind of robotics and then visual understanding, but in an active perceptive loop. So that was very inspiring, and again, that's kind of a second major reshaping of my research taste. And then graduated, went to NVIDIA. NVIDIA is still my first and only full time job, and I've been carrying on a lot of ideas from my PhD work into building general purpose robotics and robot foundation models. And sorry, that's a very, very long intro, but I do hope to look back and see kind of all, like, how all these threads tie together. You know, it's VIBE research.
00:10:27 · Molly Welch
[00:10:27] S0: What a wonderful framing, vibes based research, and so many great threads that I'm excited to pull on in our conversation today over the several exciting acts of of your career so far. And maybe to touch on this first act that your internship at OpenAI, which feels, you know, it it kind of insane to conceptualize a... You know, OpenAI in the earliest days, also this type of research, which as you said, is so relevant today, and so much in the zeitgeist. These same ambitions were... Are now possible, uniquely possible with frontier models and and, high compute RL, as you described. So take us back to this first internship at OpenAI twenty sixteen. This is World of Bits before LLMs become really central to the work at at OpenAI. What was that experience like, and how did it shape your perspective on AI research and the broader industry?
00:11:29 · Jim Fan
[00:11:29] S1: Absolutely. At that time, in OpenAI, there was the OpenAI universe that I worked on, and there was also a few other exciting projects. One is the DOTA project, so that was called OpenAI five, basically to train auto agents to solve games like DOTA, and there was also actually a robotics project at that time to use high degree of freedom, shadow hands, to solve Rubik's cube. So later, we're going to talk about some research like Eureka that actually reinstantiated some of these ideas and then trained the dexterous hands to do a lot more. So I think at that time, there were a lot of building blocks, even as early as 2016, and the most significant one being reinforcement learning and sequence models. But it wasn't until 2017 and 2018 where kind of the transformer architecture comes, and then it becomes this data sponge where you can really scale on the data and compute, and you will see magic happening from pretraining. So after that moment, we're starting to get into the pre training age of foundation models, and then RO comes back, and as I mentioned, history doesn't repeat, it rhymes. RO comes back and then really takes off from this strong foundation. The foundation needs to be able to do reasoning and needs to be able to do in context learning, all of those capabilities, and then RO can push it to the next frontier. So that experience at OpenAI also inspired one of my first projects at NVIDIA. So that was a pair of projects you mentioned at the beginning, MineDojo and Voyager, where we wanted to have these embodied agents to solve Minecraft. And I I think, you know, for that project, it was also one of my excuses to play games at work. It's all for science. Right? I'm collecting data. Right? I'm not stacking up. I'm collecting data.
00:13:29 · Molly Welch
[00:13:29] S0: All in the spirit of data collection.
00:13:31 · Jim Fan
[00:13:31] S1: It's it's all for AI. It's all for pushing the frontier of AI. So I think what was fun about that project was Minecraft is this open ended environment. It's also a simulation, meaning that you can basically generate infinite data of almost infinite diversity in Minecraft. Minecraft. I've seen people doing crazy things inside this sandbox game, right, like building the Hogwarts Castle brick by brick or even building a functioning CPU circuit using those, like, fundamental building blocks in Minecraft that actually makes the game Turing complete. So this game has infinite diversity, yet humans played it very well, but for AI, it was lagging way behind. It couldn't even do some basic things. So at a time when we started the Voyager project, that coincides with the introduction of g d four. That was the first foundation model that can do coding extremely well. So how we apply g d four to Minecraft is that we give it an API so that g d four can read the instructions of the Minecraft API and then write code, and then we execute that code in the Minecraft simulator to drive the agent to mine blocks, right, to explore, to travel, right, to dig, to craft new items. So, basically, we we we turned the game into a text environment, and it communicates by code. And then we found that g d four is not only good at in context learning, it's also very good at a capability called self reflection, so it can run through a box. No one can write perfect program at the beginning, like in one shot, not even experienced programmers. You've got to iterate, and that's what we observed with gmd4. It writes code, tests it, and the code breaks, it sees bug, it debugs, it tries again, and once it writes a good code, a good piece of code, it would commit to a memory, so we call this kind of an on the fly code repo. So g m d four will save some of the the code it wrote to this repo, so later it can retrieve it if it sees a similar situation. And in this way, we we couldn't actually fine tune the parameters of a GD four, but it still learns over time because it's committing code, retrieving code, and doing trial and error, and it accumulates the context as it goes. So it's a kind of in context lifelong learning.
00:15:59 · Jim Fan
And I find that idea really fascinating because at that time, people were really trying to experiment and see what are the capabilities of these coding frontier models, and Voyager provided one way to build a very complex agentic system on top. And then two years later, these days, the the agents are a lot more powerful. Like, self reflection, people don't even talk about it. It's kind of a given. Right? Like, all the cloud and cursor of the world, they can do debugging super well. They can go on, like, a thirty minute session to to implement a pull request, and then it just... It goes on autopilot, and it it typically does the job pretty well. And it's also able to call all kinds of tools, web browsing, connecting to MCP. So I think the field has gone way beyond Voyager, way beyond Minecraft, so that was that was really exciting to see. Now what was lacking a bit from Voyager was actually that we didn't solve the motor control problem, and we didn't solve the perception problem. We essentially simplified the problem by turning Minecraft into a set of code API and code execution environment, but later, I have come to understand that really the most difficult part may not necessarily be the reasoning side. I think the field is already solving reasoning quite well. The most difficult part of Embodied Agent is actually the low level control, the part where you interact with the low level physics. In Minecraft, it's the game physics, but in the real world, it's the actual physical reality that we're touching, and that makes the robotics problem a lot harder.