Stars
[NeurIPS 2025] Video World Models with Long-term Spatial Memory
Unified Codebase for Advanced World Models.
ActionCodec: What Makes for Good Action Tokenizers
One framework to evaluate any VLA model on any robot simulation benchmark.
Official implementation of "SeedPolicy: Horizon Scaling via Self-Evolving Diffusion Policy for Robot Manipulation".
GigaWorld-Policy: An Efficient Action-Centered World–Action Model
Helios: Real Real-Time Long Video Generation Model
Official Repository of "[ICLR26] TRAPO: A Semi-Supervised Reinforcement Learning Framework for Boosting LLM Reasoning"
CVPR2025 | TASTE-Rob: Advancing Video Generation of Task-Oriented Hand-Object Interaction for Generalizable Robotic Manipulation
Benchmarking memory-augmented robotic generalist policies
🐾 OpenClaw 101 — 从零开始，7天掌握你的AI私人助理 | 全网资源聚合站
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
A curated skill collection for academic writing and research
[Nature 2026] Merlin is a 3D VLM for computed tomography that leverages both structured electronic health records (EHR) and unstructured radiology reports for pretraining.
Interactive World Simulator for Robot Policy Training and Evaluation
This is the official codebase for paper: Scaling Verification Can Be More Effective than Scaling Policy Learning for Vision-Language-Action Alignment
🏂 World Guidance: World Modeling in Condition Space for Action Generation
Official implementation of Spatial-Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model [ICLR2026]
Official implementation of FRAPPE: Infusing World Modeling into Generalist Policies via Multiple Future Representation Alignment
RynnBrain: Open Embodied Foundation Models
Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Models
Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals
Elevate your AI research writing, no more tedious polishing ✨
📚 A curated list of Awesome Efficient dLLMs Papers with Codes