What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling

arXiv:2609.34981 · cs.CV, cs.RO · Submitted 2026-09-28 · Read on arXiv

cs.CV, cs.RO

Submitted: 2026-09-28

Updated: 2026-09-29

Project page: https://zrporz.github.io/Simple-WAM-Web

Terminology

• Generalization — 58× in this paper · explained in 13 episodes
• Generalizability — 6× in this paper · explained in 6 episodes
• Robustness — 5× in this paper · explained in 5 episodes
• Benchmark — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Conference on Computer Vision and Pattern Recognition — 2× in this paper
• World Model — 2× in this paper · explained in 7 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Closed-Loop Control — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Embodied AI — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Sample Efficiency — 1× in this paper · explained in 4 episodes
• Vision-Language-Action (VLA) Models — 1× in this paper · explained in 2 episodes

Sources

• $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
• GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation
• Benchmarking Vision, Language, & Action Models in Procedurally Generated, Open Ended Action Environments
• Efficient-WAM: A 1B-Parameter World-Action Model with Low-Cost Future Imagination
• Causal World Modeling for Robot Control
• Light-WAM: Efficient World Action Models with State-Fusion Action Decoding
• Being-H0.7: A Latent World-Action Model from Egocentric Videos
• mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs
• MemoryVLA++: Temporal Modeling via Memory and Imagination in Vision-Language-Action Models
• Wan: Open and Advanced Large-Scale Video Generative Models
• VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
• Fast-WAM: Do World Action Models Need Test-time Future Imagination?
• Keep the Future, Drop the Rollout: RIFT for World Action Models
• ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?
• Faster-WAM: Efficient Inference-Time Future Conditioning for Robust World Action 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