MARS: Systematic Multi-Level Acceleration for World Action Models
cs.CV
Submitted: 2026-10-12
Updated: 2026-10-12
Code: https://github.com/PKU-VaLuE-Lab/MARS
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Cosmos World Foundation Model Platform for Physical AI
- Flash-WAM: Modality-Aware Distillation for World Action Models
- RynnVLA-002: A Unified Vision-Language-Action and World Model
- Vidar: Embodied Video Diffusion Model for Generalist Manipulation
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- Block-wise Adaptive Caching for Accelerating Diffusion Policy
- OpenVLA: An Open-Source Vision-Language-Action Model
- Efficient-WAM: A 1B-Parameter World-Action Model with Low-Cost Future Imagination
- Causal World Modeling for Robot Control
- Dream-Tac: A Unified Tactile World Action Model for Contact-Rich Robot Manipulation
- RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots
- ActionCache: Training-Free Acceleration for Vision-Language-Action Models with Action Caching and Refinement
- mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs
- GigaWorld-Policy: An Efficient Action-Centered World--Action Model
- World Action Models are Zero-shot Policies
- Fast-WAM: Do World Action Models Need Test-time Future Imagination?
- X-Cache: Cross-Chunk Block Caching for Few-Step Autoregressive World Models Inference
- CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models
- C$^3$ache: Accelerating World Action Models with Cross Inference Chunk Cache
- Characterizing Vision-Language-Action Models across XPUs: Constraints and Acceleration for On-Robot Deployment
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