SteerQuant: Steering Quantization Error with Action-Guided Scaling in World-Action Models
cs.RO
Submitted: 2026-09-30
Updated: 2026-09-30
Terminology
Sources
- ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models
- MosaicQuant: Inlier-Outlier Disaggregation for Unified 4-Bit LLM Quantization
- Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning
- OnlineWM: Causality-Aware Active Online Learning for Effective World Modeling
- Cosmos 3: Omnimodal World Models for Physical AI
- HALO: A Unified Vision-Language-Action Model for Embodied Multimodal Chain-of-Thought Reasoning
- TwinQuant: Learnable Subspace Decomposition for 4-Bit LLM Quantization
- World Action Models are Zero-shot Policies
- Fast-WAM: Do World Action Models Need Test-time Future Imagination?
- QuantWAMs: Calibrating at the Right Granularity for World Action Models
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