[RSS 2025] Learning to Act Anywhere with Task-centric Latent Actions

🔥 SpatialVLA: a spatial-enhanced vision-language-action model that is trained on 1.1 Million real robot episodes. Accepted at RSS 2025.

[ICLR'25] LLaRA: Supercharging Robot Learning Data for Vision-Language Policy

Control your SO-100 and SO-101 robot and train VLA AI robotics models

[CVPR 2025, Spotlight] SimLingo (CarLLava): Vision-Only Closed-Loop Autonomous Driving with Language-Action Alignment

Official implementation for "FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving"

Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning

📚这个仓库是在arxiv上收集的有关VLN，VLA, SLAM，Gaussian Splatting,非线性优化等相关论文。每天都会自动更新！issue区域是最新10篇论文

🦾 A Dual-System VLA with System2 Thinking

ML platform for training, versioning, and experimenting with VLM and VLA models at scale

Pretraining code for FLOWER VLA on OXE

Pipeline which takes raw VLA data and yields science-ready data products, i.e. star formation rates

A 🤗 LeRobot fork capable of *zero-shot* VLA inference on the so-100 with π₀

Very Large Array Image Download and Time Lapse Builder