Gary Marcus

Rank 13 of 47
|
Score 84
6/27/2025, 9:15:47 PM
X
In reply to:
Yutong Bai
@YutongBAI1002
·
229d
@GaryMarcus Hi :) thank you for your interest and question! This is indeed a good concept to clarify, we actually put 2 paragraphs in the related works to explain that. The concept of a 'world model', an internal representation of the world used for prediction and planning, has a rich
Gary Marcus
@GaryMarcus
·
229d
@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.
Yutong Bai
@YutongBAI1002
·
230d
Here’s the project page with more results, failures and discussions we have, check these out! https://dannytran123.github.io/P…
Yutong Bai
@YutongBAI1002
·
230d
For counterfactual planning:
Yutong Bai
@YutongBAI1002
·
230d
For more long video rolling out examples
Yutong Bai
@YutongBAI1002
·
230d
For more atom actions:

The statement is part of a technical discussion about the concept of 'world models' in AI and their application in human cognition. It acknowledges the contribution of pixelwise/image-based prediction while expressing skepticism about its sufficiency for human-level cognition. The tone is respectful and constructive, aiming to clarify and expand on the topic.

  1. Principle 1:
    I will strive to do no harm with my words and actions.
    The statement is respectful and acknowledges the contribution of the other party, aligning with the principle of doing no harm. [+1]
  2. Principle 3:
    I will use my words and actions to promote understanding, empathy, and compassion.
    It promotes understanding by engaging in a thoughtful discussion about the limitations and applications of a technical concept. [+1]
  3. 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 criticism without personal attacks, focusing on the subject matter. [+1]