Marble: A Multimodal World Model • Hacker News Board

Re: Marble: A Multimodal World Model

#81

Post by whizzter » Thu, Nov 13, 2025, 6:24 PM UTC

AlexisArgyriou wrote: post #44

whizzter wrote: post #15

Earlier quoted context omitted.

Games are still mostly polygon based due to tooling (Even Unreal Nanite is a special variation of handling polygons), some engines have tried voxels (Teardown, Minecraft genererates polygons and would fall in the previous category as far as rendering goes) or even implict surface modes by composing SDF'y primitives (Dreams on Playstation and more recently unbound.io). All of these have fairly "exact" representations,…

You could in theory combine point clouds and Nanite: cull sub-pixel points and generate geometry on the fly by filling the voids between remaining points with polygons. The main issue is bandwidth, GPUs are barely able to handle Nanite; and this would be at least an order of magnitude more complex to do at runtime. Nanite is doing a lot of offline precomputation, storing some sort of intermediate models etc.

I agree, but I don't think this work is for realtime creation (like those Google models) but rather offline authoring. So the fixups can be done later.

Re: Marble: A Multimodal World Model

#82

Post by culi » Thu, Nov 13, 2025, 6:43 PM UTC

I just want to give it a picture of my house and have it show what it could look like organized so I know where to put everything

Re: Marble: A Multimodal World Model

#83

Post by Jayakumark » Thu, Nov 13, 2025, 6:52 PM UTC

culi wrote: post #82

I just want to give it a picture of my house and have it show what it could look like organized so I know where to put everything

Got the same use case, i tried last month with gemini app and it was awful, most rendering was messed up.

Re: Marble: A Multimodal World Model

#84

Post by Tadpole9181 » Thu, Nov 13, 2025, 7:58 PM UTC

chaosprint wrote: post #71

Feifei is a great researcher. But to be honest, the progress her company has made in "world modeling" seems to deviate somewhat from what she has advertised, which is a bit disappointing. As this article ( https://entropytown.com/articles/2025-11-13-world-model-lecu... ) summarizes, she is mainly working on 3DGS applications. The problem is that, despite the substantial funding, this demo video clearly avoids the ess…

I'm confused, the article talks about static generation. It creates a gaussian splat or models, which are rendered by an engine. This isn't a real-time model or a normal video generator like Sora, or am I misreading?

Re: Marble: A Multimodal World Model

#85

Post by robotresearcher » Thu, Nov 13, 2025, 9:32 PM UTC

dvrp wrote: post #19

Isn't this a Gaussian Splat model? I work in AI and, to this day, I don't know what they mean by “world” in “world model”.

Broadly 'world' means 'the domain I'm interested in'. In current use in the DNN context 'world' tends to be physical space at a scale relevant to humans or robots (eg. autonomous vehicles). So when someone says 'world model' you have to ask 'what kind of world, and how is it represented?'.

We don't need to agree on one very specific meaning, which is good, because we would fail.

Re: Marble: A Multimodal World Model

#86

Post by grantcas » Fri, Nov 14, 2025, 4:49 PM UTC

Marshferm wrote: post #59

saretup wrote: post #41

Earlier quoted context omitted.

histrionic and meretricious

those two words only describe AI models, as they are models. A "world model" is worse than those two words as it is oxymoronic. The idea that words and space are being conflated as a formula for spatial intelligence is fundamentally absurd as our relationships to space have no resolution, both within any one language and worse, between them, as language is arbitrary. Language and thought are entirely separate forms.…

[dead]

Re: Marble: A Multimodal World Model

#87

Post by pankajdoharey » Sat, Nov 15, 2025, 5:46 AM UTC

This is not a world model, this ise at best the reimplementation of the the NVIDIA prior art around NeRF / 3D Gaussian Splatting and monocular depth, wrapped in a nice product and workflow. What they’re actually shipping is an offline asset generator: you feed it text, images, or video, it runs depth/structure estimation and neural 3D reconstruction, and you get a static splat/mesh world you can then render or simulate in a real engine. That’s useful and impressive engineering, but it’s very different from a proper “world model” in the RL/embodied‑AI sense. Here there’s no online dynamics, no agent loop, and no interactive rollouts; it’s closer to a high‑end NeRF/GS pipeline plus tooling than to something like Google’s Genie/2/3, which actually couples generative rendering with action‑conditioned temporal evolution. Calling this a “world model” feels more like marketing language than a meaningful technical distinction. Infact my definition of a world model is more closer to what Demis has hinted in his discussions, that video gen models like veo are able to intuit they physics from just video trainingdata suggest that there is an underlying manifold in reality that is essentially computable and thus is being simulated by these models. Building such a model would essentially mean building a physics engine of some kind that predicts this manifold.