Gary Marcus

Rank 13 of 47

Score 84

@YutongBAI1002 what’s your definition of a “world model”?

this is an interesting paper but different from e.g., a scene graph or set of entities and locations and trajectory like you might find in a physics engine.

6/27/2025, 8:26:53 PM

In reply to:

Yutong Bai

@YutongBAI1002

229d

Here’s the project page with more results, failures and discussions we have, check these out! https://dannytran123.github.io/P…

Yutong Bai

@YutongBAI1002

229d

For counterfactual planning:

Yutong Bai

@YutongBAI1002

229d

For more long video rolling out examples

Yutong Bai

@YutongBAI1002

229d

For more atom actions:

Yutong Bai

@YutongBAI1002

229d

Let’s see some pixels!
We mainly showcase three types of results - atom actions, long video rollouts and counterfactuals for planning.

Yutong Bai

@YutongBAI1002

229d

What would a World Model look like if we start from a real embodied agent acting in the real world?

It has to have: 1) A real, physically grounded and complex action space—not just abstract control signals. 2) Diverse, real-life scenarios and activities.

Or in short:
It has to

The statement is a technical inquiry about the definition of a 'world model' in the context of a research paper. It seeks clarification and engages in a scholarly discussion about the differences between a world model and other concepts like scene graphs or physics engines. The tone is inquisitive and academic, aiming to deepen understanding of the research topic.

Principle 3:
I will use my words and actions to promote understanding, empathy, and compassion.
The statement promotes understanding by asking for clarification on a complex topic, fostering a deeper discussion. [+1]
Principle 4:
I will engage in constructive criticism and dialogue with those in disagreement and will not engage in personal attacks or ad hominem arguments.
The statement engages in constructive dialogue by seeking to understand different perspectives on the concept of a world model. [+1]