@AdinaYakup: BAAI just released the Orca paper on @HuggingPapers A Multimodal Latent World Model: it learns the world itself first, …
Summary
BAAI released the Orca paper describing a multimodal latent world model that learns a unified world representation first, then decodes into text, images, or actions using frozen backbones and tiny decoders, with weights coming soon.
View Cached Full Text
Cached at: 07/01/26, 10:05 AM
BAAI just released the Orca paper on @HuggingPapers
A Multimodal Latent World Model: it learns the world itself first, and text/images/actions are just different ways to read it out
How? They froze the whole backbone and only trained tiny decoders on top. So any win is the representation, not the decoder. And it scales across all 3 at once.
Weights coming soon!
Similar Articles
Orca: The World is in Your Mind
This paper introduces Orca, a world foundation model that learns a unified latent space from multimodal data using next-state-prediction, outperforming specialized baselines on downstream tasks like text generation, image prediction, and embodied action generation.
@_akhaliq: Orca The World is in Your Mind
Orca is a research paper about a language model that claims to understand the world through its own reasoning.
@artemZholus: thanks! in the second paper (https://arxiv.org/abs/2605.06388) we used your (and RAE's) recipe and it worked.
This paper systematically compares reconstruction-based and semantic latent spaces for action-conditioned latent diffusion world models in robotics. It finds that semantic encoders like V-JEPA 2.1 generally outperform reconstruction encoders on policy-relevant metrics, advocating for semantic latent spaces as a stronger foundation for robotics world models.
@mli0603: This is THE moment of Physical AI! We are officially announcing Cosmos 3: Omnimodal World Models for Physical AI - Cosm…
Announcing Cosmos 3, an omnimodal world model for Physical AI that can understand and generate language, images, video, audio, and actions within a unified architecture.
@HuggingPapers: Top AI Papers of The Week (May 25-31): - Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players - SkillO…
A curated roundup of top AI papers from May 25-31, covering multi-agent world modeling, vision-language-action models, agent skill optimization, and alignment frameworks.