arXiv Computer Vision
Zero-shot World Models Are Developmentally Efficient Learners
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Machine Learning
Oct 23
Learning Robot Behavior Priors from Non-Robotic Synthetic Data
The paper explores whether inexpensive, procedurally generated synthetic data can provide useful priors for robot learning models before any real-world data is observed. By creating three data generation pipelines that capture mathematical abstractions of robotic control, the authors pretrain a Transformer and evaluate its zero‑shot action prediction on unseen physical robot tasks. The results show that the model achieves non‑trivial performance via in‑context learning, with specialized control priors outperforming generic causal priors, though a compute‑matched real‑robot baseline still excels on its own training datasets.
arXiv Computer Vision
Sep 2
ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training
ZimaBlue is a scalable framework that learns generalizable World Action Models (WAMs) from large-scale egocentric videos. It follows a three-stage curriculum: causal video pre‑training, video‑action mid‑training with a unified action representation, and final specialization to a target robot. The system employs an asynchronous Slow‑Fast architecture to enable real‑time 30 Hz action prediction, achieving a jump in real‑robot zero‑shot success from 36.1% to 77.8% when leveraging over 120,000 hours of embodied video.
arXiv Computer Vision
Sep 22
NeuIDO: Neural Intrinsic Dynamics Operator for Physics-Informed 4D World Models
arXiv:2609.24313v1 Announce Type: new Abstract: World models aim to capture environmental dynamics and predict future trajectories, showing growing potential for embodied intelligence. Physics-inform...
arXiv AI
Jun 16
Kairos: A Native World Model Stack for Physical AI
arXiv:2606. 16533v1 Announce Type: new Abstract: World models are transitioning from passive visual generators to foundational, operational infrastructure for Physical AI: they must natively acquire world knowledge from heterogeneous experience, maintain persistent states over long horizons, and execute efficiently within real deployment constraints.
arXiv Computer Vision
Sep 22
CausalWM: Causal Chain-of-Thought Reasoning for Embodied World Model
arXiv:2609.23184v1 Announce Type: new Abstract: Embodied world models learn to predict future physical dynamics from visual observations and control signals, where physical knowledge is implicitly en...
arXiv Machine Learning
Oct 15
Imagining Goals with Geometric Horizon Models for Policy Generalization
arXiv:2610.19129v1 Announce Type: new Abstract: Training from offline data has allowed for substantial progress in domains such as robotics, leading to general-purpose policies that can be easily app...