ActTune: Action-Aware Precision and GPU Operating-Point Adaptation for Energy-Efficient Vision-Language-Action Inference
cs.RO, cs.AR
Submitted: 2026-10-06
Updated: 2026-10-06
Terminology
Sources
- ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models
- GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
- OpenVLA: An Open-Source Vision-Language-Action Model
- Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
- AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
- LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning
- Saliency-Aware Quantized Imitation Learning for Efficient Robotic Control
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- Mix-QVLA: Task-Evidence-Aware Mixed-Precision Quantization of Vision-Language-Action Models
- A Motion-Aware Vector Quantization Framework with Centroid Reuse for Efficient VLA Inference
- Towards Greener LLMs: Bringing Energy-Efficiency to the Forefront of LLM Inference
- DynamoLLM: Designing LLM Inference Clusters for Performance and Energy Efficiency
- The Impact of GPU DVFS on the Energy and Performance of Deep Learning: an Empirical Study
- SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
- VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching
- QVLA: Not All Channels Are Equal in Vision-Language-Action Model's Quantization
- EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models
- DyQ-VLA: Temporal-Dynamic-Aware Quantization for Embodied Vision-Language-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
- 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