ACG-WAM: World-Action Modeling via Action-Conditioned Geometric Latent Prediction

cs.RO

Submitted: 2026-10-03

Updated: 2026-10-03

Code: https://github.com/RoboOpus/ACG-WAM

Project page: https://roboopus.github.io/ACG-WAM

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
• JEPA-WAM: Learning Vision-Language-Action Policies with Joint-Embedding World Modeling
• WAM4D: Fast 4D World Action Model via Spatial Register Tokens
• Learning 4D Geometric Priors for Inference-Efficient World Action Models
• Qwen3-VL Technical Report

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies