Sparse-WAM: Accelerating World Action Models via Action-Guided Sparse Imagination
cs.RO, cs.AI
Submitted: 2026-09-30
Updated: 2026-09-30
Terminology
Sources
- Motus: A Unified Latent Action World Model
- LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies
- LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
- WorldCache: Accelerating World Models for Free via Heterogeneous Token Caching
- MosaicQuant: Inlier-Outlier Disaggregation for Unified 4-Bit LLM Quantization
- Efficient-WAM: A 1B-Parameter World-Action Model with Low-Cost Future Imagination
- Metis: A Generalizable and Efficient World-Action Model for Autonomous Driving and Urban Navigation
- Light-WAM: Efficient World Action Models with State-Fusion Action Decoding
- Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference
- SAFE-Pruner: Semantic Attention-Guided Future-Aware Token Pruning for Efficient Vision-Language-Action Manipulation
- OnlineWM: Causality-Aware Active Online Learning for Effective World Modeling
- Cosmos 3: Omnimodal World Models for Physical AI
- Action-aware Dynamic Pruning for Efficient Vision-Language-Action Manipulation
- HALO: A Unified Vision-Language-Action Model for Embodied Multimodal Chain-of-Thought Reasoning
- SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning
- TwinQuant: Learnable Subspace Decomposition for 4-Bit LLM Quantization
- VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- GigaWorld-Policy: An Efficient Action-Centered World--Action Model
- World Action Models are Zero-shot Policies
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
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
- Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving