FASTER: Rethinking Real-Time Flow VLAs

[ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation" & Causal Forcing++

HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos

Depth Anything 3

[CVPR 2026] Official implementation of "ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models"

A Python framework for GPU-accelerated simulation, robotics, and machine learning.

[CoRL 2025] UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations

Official implementation of PointACT: Vision-Language-Action Models with Multi-Scale Point-Action Interaction (RSS'26).

✨✨Official implementation of BridgeVLA and BridgeVLA++

Simulation Platform from AgiBot

AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing

FlashRT is a high-performance realtime inference engine for small-batch, latency-sensitive AI workloads. The flagship integration is production VLA control for Pi0, Pi0.5, GROOT N1.6, and Pi0-FAST.…

Official codebase for Fast-WAM: Do World Action Models Need Test-time Future Imagination?

Official code for world model Kairos

Lightweight coding agent that runs in your terminal

A unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats. A centralized gateway for p…

PyTorch implementation of MeanFlow & iMF (one-step generative modeling).

From Vision-Language-Action Models to a Real-World Robot Learning Stack

A high-throughput and memory-efficient inference and serving engine for LLMs

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.

[CVPR 2026] The official PyTorch implementation of the "Vision Transformer Needs More Than Registers".

First-principles design and training of a GeneralistAI Gen-1 style model, with decisions grounded in theory and supported by public evidence. Ongoing work.

The agent that grows with you

We release Evo-RL, the opensource real-world offline RL on So-101 and AgileX PiPER for easier reproduction.

TradingAgents: Multi-Agents LLM Financial Trading Framework