MT-WAM: Reorienting the One-Pass Predictive Representation Toward Action Generation

arXiv:2609.21474 · cs.CV, cs.RO · Submitted 2026-09-18 · Read on arXiv

cs.CV, cs.RO

Submitted: 2026-09-18

Updated: 2026-09-18

Code: https://github.com/Alexi1984/MT-WAM

Terminology

• KV cache — 11× in this paper · explained in 3 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Benchmark — 6× in this paper · explained in 2 episodes
• Transformer — 6× in this paper · explained in 2 episodes
• Generalization — 4× in this paper · explained in 13 episodes
• World Model — 4× in this paper · explained in 7 episodes
• Distribution Shift — 3× in this paper · explained in 5 episodes
• Embeddings — 3× in this paper · explained in 2 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Latent Space — 2× in this paper · explained in 7 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Abstraction — 1× in this paper · explained in 1 episode
• Action Chunking — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Diffusion Policy (DP) — 1× in this paper · explained in 2 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Objective Mismatch — 1× in this paper · explained in 2 episodes
• Optical Flow — 1× in this paper · explained in 2 episodes
• Rectified Flow — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• VLA Models — 1× in this paper · explained in 3 episodes

Sources

• Fast-WAM: Do World Action Models Need Test-time Future Imagination?
• Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models
• How Should World Models Be Evaluated for Embodied Decision-Making? A Decision-Making-Centric Position
• ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?
• FoMoVLA: Bridging Visual Foresight and Motion Guidance for Vision-Language-Action Models
• Track4Action: Distilling World-Centric 3D Tracker into Vision-Language-Action Policies
• Making Foresight Actionable: Repurposing Representation Alignment in World Action Models
• GeoSem-WAM: Geometry- and Semantic-Aware World Action Models
• EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Data
• Point Tracking Improves World Action Models
• FlowWAM: Optical Flow as a Unified Action Representation for World Action Models
• Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising
• Learning 4D Geometric Priors for Inference-Efficient World Action Models
• DreamWAM: Beyond RGB Future Prediction for World Action Models
• MV-WAM: Manifold-Aware World Action Model with Value Augmentation
• WorldVLA: Towards Autoregressive Action World Model
• SG-WAM: Self-Guided World Modeling in Geometry-Aware Policy Space
• ST-WAM: Semantic-Temporal World Action Model for Robust Manipulation under Visual Distribution Shifts
• 4D-WAM: Infusing Spatiotemporal Awareness into World Action Models through Trajectory Fields
• ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold 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