[HN Gopher] KumoRFM: A Foundation Model for In-Context Learning ...
       ___________________________________________________________________
        
       KumoRFM: A Foundation Model for In-Context Learning on Relational
       Data
        
       Author : cliffly
       Score  : 99 points
       Date   : 2025-05-23 06:50 UTC (16 hours ago)
        
 (HTM) web link (kumo.ai)
 (TXT) w3m dump (kumo.ai)
        
       | simplesort wrote:
       | Jure Leskovec was my Professor at Stanford a few years back, cool
       | to see he's behind this.
       | 
       | He seemed like a good guy and got the sense that he was destined
       | to do something big
        
         | stuartjohnson12 wrote:
         | Vid is a good friend of mine and he's wicked smart and also a
         | very solid guy I adore.
         | 
         | I'm also guessing at some point he will probably read this
         | comment, so hey Vid! See you at the next VRSA meetup!
        
           | andraz wrote:
           | Wickedly smart team indeed!
        
       | Rohitcss wrote:
       | A real-time in-context label generator. Nice...
        
       | bookworm123 wrote:
       | I feel like this is the next big thing for AI, having the ability
       | to interact with any sort of structured dataset out of the box.
       | Very cool project!
        
         | perbu wrote:
         | I'll suspect it'll be more like the next little thing. Most of
         | don't interact that much with structured data, so the
         | applications will be very specific.
         | 
         | However, the algo-trading crowd, will likely be very interested
         | in this. They deal with structured data all day and it would
         | surprise me if most of them don't already have things like this
         | working in their networks. They seem to be very secretive,
         | though, so we're not gonna hear much.
        
           | cliffly wrote:
           | We all interact with structured data models constantly, like
           | literally thousands of times each day, just indirectly.
           | 
           | Every single credit card purchase gets classified by a model
           | as fraud or ok. When you go to Netflix and see recommended
           | movies, it's all predictions on structured data. Every single
           | post in every social media feed is there because a model
           | predicted you'd like it.
           | 
           | Realistically, it might be more like 10s of thousands or even
           | hundreds of thousands of predictions that we engage with in a
           | day.
           | 
           | If reality matches the benchmarks for this model, it can kick
           | off a whole new category of models that can potentially be
           | bigger than LLMs
        
           | gk1 wrote:
           | Structured data = relational data
           | 
           | This has more applications than you might first think.
        
         | hbarka wrote:
         | Does AI for relational data work the same way as token
         | predictions does for LLM AI?
        
       | tinyoli wrote:
       | Strange that they do not compare it against TabFN, which is
       | another foundation model for tabular data.
       | (https://github.com/PriorLabs/TabPFN)
        
         | profjure wrote:
         | TabPFN is an amazing innovation. But there are some crucial
         | differences in model capabilities that make it hard for a fair
         | comparison.
         | 
         | TabPFN can only operate on a single small table. But real-world
         | datasets are actually multi-table and to make accurate
         | prediction you need to capture signal from multiple tables (for
         | example, customers, products, purchases).
         | 
         | So, the comparison to TabPFN would be unfair as it would only
         | use data from a single table and that would lead to bad
         | performance of TabPFN.
        
       | SubiculumCode wrote:
       | So suppose I've got a database of behavioral and neuroimaging
       | data from a research study on autism. Is this something that can
       | be used to predict diagnosis from the other data fields?
        
         | profjure wrote:
         | Yes, I think this would work. For example, you'd organize the
         | data into 3 tables: patients, behaviors and images. The
         | patients table would have a partially filled-out "diagnosis"
         | column. The model would then predict diagnosis of not-yet-
         | diagnosed patients based on the patterns in data fields of
         | previously diagnosed patients.
        
       | EGreg wrote:
       | So can this be used to predict patterns for traffic, restaurant
       | table availability, and your customers' demand for things based
       | on other customers?
        
         | autorinalagist wrote:
         | Hey! I'm one of the engineers who worked on this project.
         | 
         | These are all problems that KumoRFM is able to solve given that
         | you have the right relational data of course! So e.g. for
         | predicting restaurant table availability you would need at
         | least an occupancy table which records how many seats were
         | available historically and you can predict its future entries.
         | 
         | But you can also add more relevant data without joining into a
         | single table, so you can add a restaurants table, a holiday-
         | calendar table, weather patterns, etc. and KumoRFM should take
         | it all into account when predicting.
        
       | nsbk wrote:
       | Interesting timing, they have recently reached out to my $dayjob.
       | We will be probably be running a workshop on our (massive)
       | dataset with them. I'd like to evaluate the performance of a
       | couple of analytical models we've manually built against whatever
       | this model can do based on some prompts. Exciting times!
        
       | dcrimp wrote:
       | interesting! Super cool idea to augment software built with
       | traditional DBs
       | 
       | I had some thoughts [1] around a concept similar to this a while
       | ago, although it was much less refined. My thinking was around
       | whether or not we could have a neural net remember a relational
       | database schema, and be able to be queried for facts it knows,
       | and facts it might predict.
       | 
       | This seems like a much more sensical (and actualised) stab at
       | this kinda concept.
       | 
       | [1]: dancrimp.nz/2024/11/01/semantic-db/
        
       ___________________________________________________________________
       (page generated 2025-05-23 23:01 UTC)