CraftJarvis / ROCKET-2
Official Implementation of Paper "ROCKET-2: Steering Visuomotor Policy via Cross-View Goal Alignment"
☆35Updated last month
Alternatives and similar repositories for ROCKET-2
Users that are interested in ROCKET-2 are comparing it to the libraries listed below
Sorting:
- Official implementation of paper "ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context Prompting" (CVPR 2025)☆41Updated last month
- GROOT: Learning to Follow Instructions by Watching Gameplay Videos (ICLR 2024 Spotlight)☆64Updated last year
- Official Implementation of "JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse"☆73Updated last month
- ☁️ KUMO: Generative Evaluation of Complex Reasoning in Large Language Models☆17Updated 3 weeks ago
- [NeurIPS 2024] Official Implementation for Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks☆73Updated last month
- MineWorld: A Real-time interactive world model on Minecraft☆321Updated last week
- [NeurIPSw'24] This repo is the official implementation of "MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simu…☆89Updated 3 months ago
- MineStudio: A Streamlined Package for Minecraft AI Agent Development☆238Updated this week
- Official repo of EmbodiedBench, a comprehensive benchmark designed to evaluate MLLMs as embodied agents. (ICML 2025)☆120Updated 2 weeks ago
- [ICLR 2025 Oral] PyTorch code for the paper "Open-World Reinforcement Learning over Long Short-Term Imagination"☆112Updated last week
- ☆136Updated this week
- [CVPR2024] This is the official implement of MP5☆101Updated 10 months ago
- [ICML'25] The PyTorch implementation of paper: "AdaWorld: Learning Adaptable World Models with Latent Actions".☆72Updated this week
- ☆102Updated last month
- RoboFactory: Exploring Embodied Agent Collaboration with Compositional Constraints☆44Updated last month
- MetaSpatial leverages reinforcement learning to enhance 3D spatial reasoning in vision-language models (VLMs), enabling more structured, …☆117Updated last week
- An open-source lightweight game generation paradigm. It includes everything from data processing to model architecture design and playabi…☆86Updated 4 months ago
- [ArXiv 2025] WorldMem: Long-term Consistent World Simulation with Memory☆124Updated last week
- Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks☆104Updated last week
- ☆28Updated 10 months ago
- Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations https://video-prediction-policy.github.io☆135Updated this week
- ☆126Updated 4 months ago
- Official implementation of "Self-Improving Video Generation"☆66Updated 3 weeks ago
- (VillagerAgent ACL 2024) A Graph based Minecraft multi agents framework☆59Updated this week
- ☆33Updated last month
- ☆18Updated last week
- Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long c…☆317Updated last month
- VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework☆326Updated last week
- A comprehensive list of papers for the definition of World Models and using World Models for General Video Generation, Embodied AI, and A…☆122Updated 2 weeks ago
- Official repository of S-Agents: Self-organizing Agents in Open-ended Environment☆26Updated last year