Q-WAM: 4-Bit Quantization of World Action Models with Action-Subspace Protection
cs.RO, cs.CV
Submitted: 2026-09-27
Updated: 2026-09-27
Terminology
Sources
- ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models
- Flash-WAM: Modality-Aware Distillation for World Action Models
- QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
- Motus: A Unified Latent Action World Model
- WorldVLA: Towards Autoregressive Action World Model
- RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
- GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
- Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning
- Causal World Modeling for Robot Control
- SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
- Q-Diffusion: Quantizing Diffusion Models
- BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction
- Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models
- AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
- Flow Matching for Generative Modeling
- SpinQuant: LLM quantization with learned rotations
- Faster-WAM: Do World Action Models Need Deep Action Modules?
- PTQ4DiT: Post-training Quantization for Diffusion Transformers
- SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language 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