Official implementation of [AstraNav-World: World Model for Foresight Control and Consistency]

📚这个仓库是在arxiv上收集的有关VLN，VLA，World Model，SLAM，Gaussian Splatting,非线性优化等相关论文。每天都会自动更新！issue区域是最新10篇论文

StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing

[RSS 2025] Learning to Act Anywhere with Task-centric Latent Actions

Open & Reproducible Research for Tracking VLAs

Simulated experiments for "Real-Time Execution of Action Chunking Flow Policies".

Official repository for OmniVLA training and inference code

A simulation platform for versatile Embodied AI research and developments.

[RSS'25] This repository is the implementation of "NaVILA: Legged Robot Vision-Language-Action Model for Navigation"

[CoRL 2025] GC-VLN: Instruction as Graph Constraints for Training-free Vision-and-Language Navigation

[CVPR 2025] UniGoal: Towards Universal Zero-shot Goal-oriented Navigation

[NeurIPS 2024] SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation

[CVPR 2025] Source codes for the paper "3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning"

RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI

[RSS 2025] Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks.

[IROS‘2025] Interactive Navigation with Learned Arm-pushing Controller

This repository summarizes recent advances in the VLA + RL paradigm and provides a taxonomic classification of relevant works.

[RA-L 2025] FrontierNet: Learning Visual Cues to Explore

VLA-0: Building State-of-the-Art VLAs with Zero Modification

[ICLR2026] Official implementation for "JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation"

SGLang is a high-performance serving framework for large language models and multimodal models.

Vision-and-Language Navigation in Continuous Environments using Habitat

Official code and checkpoint release for mobile robot foundation models: GNM, ViNT, and NoMaD.

InternRobotics' open platform for building generalized navigation foundation models.

RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning