Scope-WM: Scoped Computation for Efficient Visual World Models

arXiv:2609.33218 · cs.CV, cs.AI, cs.RO · Submitted 2026-09-27 · Read on arXiv

cs.CV, cs.AI, cs.RO

Submitted: 2026-09-27

Updated: 2026-09-27

Code: https://github.com/ChunZheng2022/Scope-WM

Terminology

• World Model — 28× in this paper · explained in 7 episodes
• Transformer — 15× in this paper · explained in 2 episodes
• Distillation — 13× in this paper · explained in 2 episodes
• Sparsity — 6× in this paper · explained in 4 episodes
• Latent Dynamics — 5× in this paper · explained in 2 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Distilled Relevance Selection — 3× in this paper
• Foreground-Delta Background Update — 3× in this paper
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• Deep Reinforcement Learning — 2× in this paper · explained in 2 episodes
• Pruning — 2× in this paper · explained in 4 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Adaptive Graph — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Sample Efficiency — 1× in this paper · explained in 4 episodes
• Task Planning — 1× in this paper · explained in 2 episodes

Sources

• V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
• Sparse Imagination for Efficient Visual World Model Planning
• Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control
• D4RL: Datasets for Deep Data-Driven Reinforcement Learning
• World Models
• Mastering Diverse Domains through World Models
• LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
• Masked Visual Pre-training for Motor Control
• DDP-WM: Disentangled Dynamics Prediction for Efficient World Models

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