Skip to content

@InternRobotics Intern Robotics

Change the repository type filter

All

    Repositories list

    60 repositories

    • F1-VLA

      Public
      F1: A Vision Language Action Model Bridging Understanding and Generation to Actions
      Python
      •10•151•4•0•Updated Jan 2, 2026Jan 2, 2026

    • internvla-a1.github.io

      Public
      The webpage of InternVLA-A1
      HTML
      •0•0•0•0•Updated Jan 1, 2026Jan 1, 2026

    • InternNav

      Public
      InternRobotics' open platform for building generalized navigation foundation models.
      Jupyter Notebook
      •
      MIT License
      •63•570•5•2•Updated Dec 31, 2025Dec 31, 2025

    • VL-LN

      Public
      VL-LN Bench: Towards Long-horizon Goal-oriented Navigation with Active Dialogs
      Python
      •
      MIT License
      •0•9•0•0•Updated Dec 30, 2025Dec 30, 2025

    • MMSI-Bench

      Public
      [arXiv 2025] MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence
      Python
      •0•67•0•0•Updated Dec 29, 2025Dec 29, 2025

    • MMSI-Video-Bench

      Public
      MMSI-Video-Bench: A Holistic Benchmark for Video-Based Spatial Intelligence
      Python
      •0•42•0•0•Updated Dec 26, 2025Dec 26, 2025

    • NavDP

      Public
      Official implementation of the paper: "NavDP: Learning Sim-to-Real Navigation Diffusion Policy with Privileged Information Guidance"
      Python
      •27•423•7•0•Updated Dec 25, 2025Dec 25, 2025

    • internrobotics.github.io

      Public
      Documentation of Intern Robotics Platform & Toolkits
      Python
      •6•2•0•3•Updated Dec 25, 2025Dec 25, 2025

    • GenManip

      Public
      [CVPR 2025] Official implementation of "GenManip: LLM-driven Simulation for Generalizable Instruction-Following Manipulation"
      roboticssimulationmanipulationisaac-sim
      Python
      •3•131•6•0•Updated Dec 23, 2025Dec 23, 2025

    • AnySplat

      Public
      [SIGGRAPH Asia 2025 (ACM TOG)] AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views
      Python
      •
      MIT License
      •32•660•32•0•Updated Dec 22, 2025Dec 22, 2025

    • CronusVLA

      Public
      [AAAI26 oral] CronusVLA: Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling
      Python
      •
      MIT License
      •2•67•0•0•Updated Dec 21, 2025Dec 21, 2025

    • InternVLA-M1

      Public
      InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy
      roboticsvision-language-modelvision-language-action-model
      Python
      •
      MIT License
      •19•324•3•0•Updated Dec 17, 2025Dec 17, 2025

    • internvla-n1-dualvln.github.io

      Public
      JavaScript
      •0•0•0•0•Updated Dec 10, 2025Dec 10, 2025

    • MeshCoder

      Public
      Jupyter Notebook
      •
      MIT License
      •21•422•8•0•Updated Dec 8, 2025Dec 8, 2025

    • G2VLM

      Public
      G2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning
      3d-reconstructionspatial-reasoningmllmsspatial-intelligence3d-llmsspatial-understanding
      Python
      •
      Apache License 2.0
      •4•241•5•0•Updated Nov 27, 2025Nov 27, 2025

    • EgoThinker

      Public
      Official implementation of EgoThinker at NIPS 2025
      Python
      •0•22•2•0•Updated Nov 25, 2025Nov 25, 2025

    • EgoHOD

      Public
      Official implementation of EgoHOD at ICLR 2025; 14 EgoVis Challenge Winners in CVPR 2024
      Python
      •
      Apache License 2.0
      •2•31•1•0•Updated Nov 25, 2025Nov 25, 2025

    • MV-CoLight

      Public
      [NIPS 2025] MV-CoLight: Efficient Object Compositing with Consistent Lighting and Shadow Generation
      Python
      •
      MIT License
      •2•14•2•0•Updated Nov 21, 2025Nov 21, 2025

    • interndata-a1.github.io

      Public
      HTML
      •0•1•0•0•Updated Nov 20, 2025Nov 20, 2025

    • StreamVLN

      Public
      Official implementation of the paper: "StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling"
      Python
      •24•364•16•1•Updated Nov 2, 2025Nov 2, 2025

    • Aether

      Public
      [ICCV 2025 & ICCV 2025 RIWM Outstanding Paper] Aether: Geometric-Aware Unified World Modeling
      navigationmulti-modalvideo-generationvideo-predictionembodied-aivisual-planning4d-reconstructionfoundation-modelsworld-model4d-generation
      Python
      •
      MIT License
      •6•555•0•0•Updated Oct 26, 2025Oct 26, 2025

    • internvla-m1.github.io

      Public
      Astro
      •0•1•0•0•Updated Oct 23, 2025Oct 23, 2025

    • Humanoid-Goalkeeper

      Public
      [arxiv 2025] Official implementation of "Humanoid Goalkeeper: Learning from Position Conditioned Task-Motion Constraints"
      Python
      •
      Other
      •7•129•0•0•Updated Oct 22, 2025Oct 22, 2025

    • InternScenes

      Public
      [NeurIPS 2025] InternScenes: A Large-scale Interactive Indoor Scene Dataset with Realistic Layouts.
      datasetscene-generationembodied-aiinteractive-scenes
      Python
      •6•206•4•0•Updated Oct 17, 2025Oct 17, 2025

    • AdaMimic

      Public
      [arxiv 2025] Official implementation of "Towards Adaptable Humanoid Control via Adaptive Motion Tracking"
      Python
      •11•188•7•0•Updated Oct 17, 2025Oct 17, 2025

    • .github

      Public
      4•0•0•0•Updated Oct 16, 2025Oct 16, 2025

    • InternManip

      Public
      An All-in-one robot manipulation learning suite for policy models training and evaluation on various datasets and benchmarks.
      Python
      •
      MIT License
      •10•167•6•0•Updated Oct 15, 2025Oct 15, 2025

    • PhysHSI

      Public
      Official implementation of the paper: "PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction System"
      roboticshumanoid
      Python
      •
      Other
      •14•223•5•2•Updated Oct 14, 2025Oct 14, 2025

    • InternHumanoid

      Public
      A versatile, all-in-one toolbox for whole-body humanoid robot control.
      Python
      •
      MIT License
      •3•155•1•0•Updated Oct 10, 2025Oct 10, 2025

    • ARTDECO

      Public
      ARTDECO unifies 3D foundation priors with structured scene representations, enabling robust and generalizable 3D reconstruction of diverse real-world scenes using only monocular video.
      8•139•0•0•Updated Oct 10, 2025Oct 10, 2025