StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing
-
Updated
Sep 5, 2026 - Python
StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing
A curated collection of papers, explainers, and resources on World Action Models for embodied AI
An all-in-one VLA engineering platform for embodied AI — from data to real-robot deployment.
Paper list in the survey paper: Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis
An Open-Source World Model for Action-Conditioned Embodied Intelligence.
A unified framework for training, fine-tuning, and evaluating World Action Models
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses | 500+ Papers | Perception, Cognition, Planning, Interaction, Agentic System
Official repository for "OpenWAM: An Open, Modular Exploration Towards Systematic World–Action Model Pretraining".
A curated list of academic papers and resources on Vision-Language-Action (VLA) and World Action Models (WAM)
Official project page and code repository for Enfold.
🌍 World Action Model · 2026 categorized index — 200+ papers (Cascaded/Joint WAM + Simulator + Video WM), synthesized from 4 surveys + 7 awesome lists
Project page for "OpenWAM: An Open, Modular Exploration Towards Systematic World–Action Model Pretraining".
A curated collection of papers, datasets, benchmarks, and code on spatial and 3D world models for reasoning, prediction, planning, and embodied intelligence.
[CoRL 2026] EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Data
Tiny DreamZero-style World Action Model for 2D tabletop manipulation
A tiny World Action Model from scratch for robot learning.
Counterfactual evaluation for World Action Models
An obsidian vault, which collects papers in the filed of Embodided AI, including VLAs, World-Action-Models etc.
Learning Tactile-Aware Quadrupedal Loco-Manipulation Policies
To associate your repository with the world-action-model topic, visit your repo's landing page and select "manage topics."