Frozen Flows Forget: Diagnosing and Restoring Lost Motion in a Latent-flow World Model

arXiv:2609.28414 · cs.CV, cs.AI, cs.RO · Submitted 2026-09-23 · Read on arXiv

cs.CV, cs.AI, cs.RO

Submitted: 2026-09-23

Updated: 2026-09-23

Code: https://github.com/Mangkhut160/icassp2027

Terminology

• World Model — 12× in this paper · explained in 7 episodes
• Decode — 10× in this paper · explained in 2 episodes
• Benchmark — 5× in this paper · explained in 2 episodes
• Sparsity — 3× in this paper · explained in 4 episodes
• Generative Model — 2× in this paper · explained in 2 episodes
• Generative Models — 2× in this paper · explained in 2 episodes
• Latent Space — 2× in this paper · explained in 7 episodes
• Latent World Models — 2× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Flow Matching — 1× in this paper · explained in 8 episodes
• Latent Dynamics — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow
• Towards Accurate Generative Models of Video: A New Metric & Challenges
• Stochastic Adversarial Video Prediction
• What Makes Video World Model Latents Action-Relevant: Prediction over Reconstruction
• SimVPv2: Towards Simple yet Powerful Spatiotemporal Predictive Learning

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