SANA & Sol: Efficient Generative Models and Full-Stack Training & Inference Engines for Image, Video, and World Modeling

[ICLR 2026] Code of "MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation"

MME-VLA-Suite

Embodied In-Context Learning for GPT-6 Astra

This repo is the official implementation of "τ0-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation".

An all-in-one VLA engineering platform for embodied AI — from data to real-robot deployment.

Python-based research interface for blackbox and hyperparameter optimization, based on the internal Google Vizier Service.

RPent: Agentic Infrastructure for the Physical World

GPT-6 Astra for embodied AI and robotics.

Code as World: Agentic Discovery of Executable World Representations for Physical Reasoning

RoboClaw is an Embodied AI Assistant.

DeepSeek Harness: Everything is a Plugin.

The roadmap of long-horizon agents

The modern alternative to LaTeX. Create PDF documents templates using React, JSX, and Tailwind

Agents' Last Exam

A cross-platform protocol library to communicate with iOS devices

Gym-Anything: Turn any Software into an Agent Environment

Train the smallest LM you can that fits in 16MB. Best model wins!

Run OpenClaw on Android with a single command — no proot, no Linux

[NeurIPS'26] SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning