What Makes an Efficient VLA? Navigating Action-Head Design, Scaling, and Latency
cs.RO, cs.CV
Submitted: 2026-09-12
Updated: 2026-09-23
Code: https://github.com/MindVLA-Team/EFFVLA
Project page: https://mindvla-team.github.io/EFFVLA
Terminology
Sources
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
- OpenVLA: An Open-Source Vision-Language-Action Model
- FAST: Efficient Action Tokenization for Vision-Language-Action Models
- Qwen2.5 Technical Report
- SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
- DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
- LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
- What Matters in Building Vision-Language-Action Models for Generalist Robots
- RT-1: Robotics Transformer for Real-World Control at Scale
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
- Octo: An Open-Source Generalist Robot Policy
- CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- Gemini Robotics: Bringing AI into the Physical World
- Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware
- VLANeXt Family: A Systematic Study of VLA Models from Core Recipes to Emerging Paradigms
- StarVLA- alpha: Reducing Complexity in Vision-Language-Action Systems
- Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution
- Surgical Fine-Tuning Improves Adaptation to Distribution Shifts
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