GALA: Geometry-Aware Latent Action Modeling for Vision-Language-Action Model Pretraining across Embodiments

arXiv:2609.21948 · cs.RO, cs.CV · Submitted 2026-09-18 · Read on arXiv

cs.RO, cs.CV

Submitted: 2026-09-18

Updated: 2026-09-18

Project page: https://puzhenyuan.github.io/GALA-website

Terminology

• Transformer — 11× in this paper · explained in 2 episodes
• Action Space — 10× in this paper · explained in 1 episode
• Geometry-Aware Latent Action — 9× in this paper
• Point Clouds — 7× in this paper · explained in 2 episodes
• Latent Representation — 6× in this paper · explained in 2 episodes
• Generalizability — 5× in this paper · explained in 6 episodes
• Alignment — 3× in this paper · explained in 1 episode
• Benchmark — 3× in this paper · explained in 2 episodes
• Unified End-effector Motion Representation — 3× in this paper
• Angular Error — 2× in this paper · explained in 1 episode
• Computer Vision and Pattern Recognition — 2× in this paper
• Core — 2× in this paper · explained in 2 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• IEEE International Conference on Robotics and Automation — 2× in this paper
• Vision-Language-Action (VLA) Models — 2× in this paper · explained in 2 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Action Flow — 1× in this paper · explained in 1 episode
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Diffusion Model — 1× in this paper · explained in 8 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• International Conference on Computer Vision — 1× in this paper
• Latent Space — 1× in this paper · explained in 7 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Self-Supervised Learning — 1× in this paper · explained in 8 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes

Sources

• OpenVLA: An Open-Source Vision-Language-Action Model
• Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
• GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
• $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
• $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
• UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent
• Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations
• METIS: Multi-Source Egocentric Training for Integrated Dexterous Vision-Language-Action Model
• Latent Action Diffusion for Cross-Embodiment Manipulation
• One-Policy-Fits-All: Geometry-Aware Action Latents for Cross-Embodiment Manipulation
• Cross-Hand Latent Representation for Vision-Language-Action Models
• UniVLA: Learning to Act Anywhere with Task-centric Latent Actions
• HARP-VLA: Human-Robot Aligned Representation Learning for Vision-Language-Action Model
• ConLA: Contrastive Latent Action Learning from Human Videos for Robotic Manipulation
• RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots
• DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control
• UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations
• FLARE: Robot Learning with Implicit World Modeling
• DiT4DiT: Jointly Modeling Video Dynamics and Actions for Generalizable Robot Control
• JoyAI-RA 0.1: A Foundation Model for Robotic Autonomy

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