The relational foundation model produces predictions via a single frozen forward pass of a transformer-like neural network using in-context learning, with no training, gradients, agent loop, memory, or scratchpad involved.
Jure clarifies that Kumo's relational foundation model is not an agent: it makes predictions through a single forward pass of a pre-trained, frozen transformer-like network with in-context examples, with no backpropagation, memory, or iterative reasoning steps. ✦ AI generated
Jure Leskovec · The TWIML AI Podcast · 2026-05-21 · original ↗
starts at this moment · 34:43
“Does the model require some type of memory structure blackboard or something in order to um you know do a scratch work to to come up with a representation or is this all like thought traces or something like that?”
No no no this is not this is not an agent. This is a single forward pass of a transformer-l like neural network. Right? So this is purely inside the neural network. There is no agent. There is no memory. There is no scratch pad. There is no let me do this, let me do that. Right? The answer is truly a single forward pass of a neural network. There is no loop.
verbatim transcript · starts at 34:43
34:43or is this all like thought traces or something like that? >> No no no this is not this is not an agent. This is a single forward pass of a transformer-l like neural network. Right? So this is purely inside the neural network. There is no agent. There is no memory. There is no scratch pad. There is no let me do this, let me do that. Right? The answer is truly a
35:07single forward pass of a neural network. There is no loop. Nothing like that. Right? So you you get the answer in I don't know 2 seconds, half a second uh whatever the time be, right? It's really a single forward pass of a pre-trained frozen neural network. There is no language model here, right? This is kind of technology that's parallel or or complementaryary to language models, right? You cannot textify a database and
35:35then go to chat GP and say, "Hey, what do you think? How how likely is this transaction to be fraudulent? You get horrible results, right? So, this is uh yeah, frozen pre-trained architecture that allows you that allows you to do that. I feel like I've gone the full cycle from that's an outlandish claim to oh yeah, I can see how that will work to I don't know. It's still
35:57kind of crazy that it works. >> Yeah. No, it's interesting, right? And when we when we test this on data sets that are locked away and hidden and the model has never been trained on and on task tasks that we haven't even thought about, we see we see a we see a gain over best supervised models out there. Right? If you would go and say, I I'll
36:20hire a data scientist. They'll spend several weeks building the model, tuning the model, the latest neural networks, whatever, this, it's still a couple of percentage points worse. Um and then if you fine-tune the let's say the foundation model uh on on on more data for the specific task then you get to this superhuman accuracy performance that you know present manual or semianual or agentic solutions uh are
- ·Single frozen forward pass of a transformer-like network
- ·No training, gradients, or backpropagation at inference
- ·No agent loop, memory, or scratchpad involved
- ·Answer is purely inside the neural network
- ·In-context learning with pre-trained frozen weights
- ·No iterative reasoning or multi-step deliberation
- ·No 'let me do this, then let me do that'
- ·Single pass produces the prediction directly