Stars
The Official Implementation of "ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow"
🐧 一个更完整、更优雅的 Linux Clash / Mihomo 代理运行平台
X-Tokenizer: A Multimodal Action Tokenizer for Vision-Language-Action Pretraining
Create beautiful slides on the web using a coding agent's frontend skills
[ICML 2026]Official PyTorch implementation of "SpecPL: Disentangling Spectral Granularity for Prompt Learning"
"World Models in a Closed-Loop World" (ICLR'26 Oral)
ManipArena-Sim is the simulation environment for ManipArena, a real-robot benchmark for bimanual manipulation. It provides data collection, replay, and policy evaluation for the bimanual robot, bui…
One framework to evaluate any VLA model on any robot simulation benchmark.
Official code of Motus: A Unified Latent Action World Model
Wan: Open and Advanced Large-Scale Video Generative Models
😼 优雅地使用基于 clash/mihomo 的代理环境
Building General-Purpose Robots Based on Embodied Foundation Model
[ICLR 2025 Oral] The official implementation of "Diffusion-Based Planning for Autonomous Driving with Flexible Guidance"
[ICLR 2026] The official implementation of "Dichotomous Diffusion Policy Optimization"
StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing
[IEEE TGRS] The Official Implementation of "UAGLNet: Uncertainty-Aggregated Global-Local Fusion Network with Cooperative CNN-Transformer for Building Extraction"
The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free
Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"
[ICLR 2026] The offical Implementation of "Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model"
😼 优雅地使用基于 clash/mihomo 的代理环境
[ACM CSUR 2025] Understanding World or Predicting Future? A Comprehensive Survey of World Models
A benchmark for offline goal-conditioned RL and offline RL
A collection of robotics simulation environments for reinforcement learning
[ICLR 2026] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
The official implementation of "Robo-MUTUAL: Robotic Multimodal Task Specification via Unimodal Learning"