Causally Debiased Latent Action Model for Embodied Action-Conditioned World Models

arXiv:2607.09185 · cs.CV, cs.RO · Submitted 2026-07-10 · Read on arXiv

cs.CV, cs.RO

Submitted: 2026-07-10

Updated: 2026-09-26

Terminology

• Adaptation — 43× in this paper · explained in 1 episode
• World Model — 38× in this paper · explained in 7 episodes
• Fine-Tuning — 22× in this paper · explained in 5 episodes
• Calibration — 16× in this paper · explained in 7 episodes
• Fidelity — 15× in this paper · explained in 2 episodes
• Action Space — 12× in this paper · explained in 1 episode
• Latent Space — 12× in this paper · explained in 7 episodes
• Contrastive Learning — 8× in this paper · explained in 5 episodes
• Robustness — 7× in this paper · explained in 5 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Consistency — 4× in this paper · explained in 3 episodes
• Action-Conditioned World Model — 3× in this paper · explained in 1 episode
• Foundation Model — 3× in this paper · explained in 3 episodes
• Action Bias — 2× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Clustering — 2× in this paper · explained in 2 episodes
• Conference on Computer Vision and Pattern Recognition — 2× in this paper
• Data Augmentation — 2× in this paper · explained in 7 episodes
• Foundation Models — 2× in this paper · explained in 7 episodes
• International Conference on Learning Representations — 2× in this paper
• Representation Learning — 2× in this paper · explained in 2 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Action Decoder — 1× in this paper · explained in 1 episode
• Action Primitives — 1× in this paper · explained in 1 episode
• CVF International Conference on Computer Vision — 1× in this paper
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Embodied AI — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Foreground Displacement Chamfer Error — 1× in this paper
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• International Conference on Machine Learning — 1× in this paper
• Semantic Similarity — 1× in this paper · explained in 2 episodes

Sources

• World Models
• Mastering Diverse Domains through World Models
• ACWM-Phys: Investigating Generalized Physical Interaction in Action-Conditioned Video World Models
• iVideoGPT: Interactive VideoGPTs are Scalable World Models
• Open X-Embodiment: Robotic Learning Datasets and RT-X Models
• Genie: Generative Interactive Environments
• Learning to Act without Actions
• DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
• ConLA: Contrastive Latent Action Learning from Human Videos for Robotic Manipulation
• AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems
• SAM 3: Segment Anything with Concepts
• EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video
• CoWTracker: Tracking by Warping instead of Correlation
• Imitating Latent Policies from Observation
• Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos
• IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI
• Learning Additively Compositional Latent Actions for Embodied AI
• Co-Evolving Latent Action World Models
• MVP-LAM: Learning Action-Centric Latent Action via Cross-Viewpoint Reconstruction
• Learning Interactive Real-World Simulators

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models