InternRobotics

A simulation platform for versatile Embodied AI research and developments.

InternRobotics' open platform for building generalized navigation foundation models.

[ECCV 2024 Best Paper Candidate & TPAMI 2025] PointLLM: Empowering Large Language Models to Understand Point Clouds

Learning-based locomotion control from OpenRobotLab, including Hybrid Internal Model & H-Infinity Locomotion Control

[SIGGRAPH Asia 2025 (ACM TOG)] AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views

[ICRA 2026] NavDP: Learning Sim-to-Real Navigation Diffusion Policy with Privileged Information Guidance

[CVPR 2024 & NeurIPS 2024] EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI

[RSS 2025 Best Systems Paper Finalist] 💐Official implementation of "Learning Humanoid Standing-up Control across Diverse Postures"

[ICRA 2026] Official implementation of the paper: "StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling"

Open-sourced code for "HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit".

[ICCV 2025 & ICCV 2025 RIWM Outstanding Paper] Aether: Geometric-Aware Unified World Modeling

[ICLR 2026]ARTDECO: Towards Efficient and High-Fidelity On-the-Fly 3D Reconstruction with Structured Scene Representation

InternVLA-A1: Unifying Understanding, Generation, and Action for Robotic Manipulation​

InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy

[CVPR 2026] G2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning

[ICML2026] VLAC: A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning

Official implementation of the paper: "PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction System"

[ICLR 2025 Oral] Seer: Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulation

[NeurIPS 2025] InternScenes: A Large-scale Interactive Indoor Scene Dataset with Realistic Layouts.

[ICLR 2024 Spotlight] Unified Human-Scene Interaction via Prompted Chain-of-Contacts

[ICRA 2026 Oral] Official implementation of "Towards Adaptable Humanoid Control via Adaptive Motion Tracking"

[RSS 2025] Novel Demonstration Generation with Gaussian Splatting Enables Robust One-Shot Manipulation

[ECCV 26] Official implementation of "SIM1: Physics-Aligned Simulator as Zero-Shot Data Scaler in Deformable Worlds "

F1: A Vision Language Action Model Bridging Understanding and Generation to Actions

[arxiv 2025] Official implementation of "Humanoid Goalkeeper: Learning from Position Conditioned Task-Motion Constraints"

[Technical Report & ICLR 2026] RoboInter1.5 & RoboInter: A Holistic Intermediate Representation Suite Towards Robotic Manipulation

A versatile, all-in-one toolbox for whole-body humanoid robot control.

[ICRA 2026] Re3Sim: Generating High-Fidelity Simulation Data via 3D-Photorealistic Real-to-Sim for Robotic Manipulation

[CVPR 2025] Official implementation of "GenManip: LLM-driven Simulation for Generalizable Instruction-Following Manipulation"

An All-in-one robot manipulation learning suite for policy models training and evaluation on various datasets and benchmarks.

[CVPR 2025] Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes

Elemental Diagnosis of Generalist Mobile Manipulation Policies

InternDataEngine: Pioneering High-Fidelity Synthetic Data Generator for Robotic Manipulation

InternW0-Δ : A World Action Model Bridging Predictive Dynamics and Actions with 20K+ Hours of Open Data

Code&Data for Grounded 3D-LLM with Referent Tokens

[CoRL 2024] VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding

[ICLR 2026] InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation

[AAAI26 oral] CronusVLA: Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling

[ICLR 2026] MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence

This is the official implementation of the voxel-based humanoid locomotion in "Gallant: Voxel Grid-based Humanoid Locomotion and Local-navigation across 3D Constrained Terrains"

[NeurIPS 2023] OV-PARTS: Towards Open-Vocabulary Part Segmentation

[ICRA 2026] UltraDexGrasp: Learning Universal Dexterous Grasping for Bimanual Robots with Synthetic Data

[IJCV 2024] P3Former: Position-Guided Point Cloud Panoptic Segmentation Transformer

[SIGGRAPH Asia 2026] M³: Dense Matching Meets Multi-View Foundation Models for Monocular Gaussian Splatting SLAM

[NeurIPS 2025 Spotlight] MesaTask: Towards Task-Driven Tabletop Scene Generation via 3D Spatial Reasoning

Cortex: A Bidirectionally Aligned Embodied Agent Framework for Long-horizon Manipulation

[NeurIPS 2025] OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding

[RSS 2025] Gripper Keypose and Object Pointflow as Interfaces for Bimanual Robotic Manipulation

Robo3R: Enhancing Robotic Manipulation with Accurate Feed-Forward 3D Reconstruction

[CoRL 2023] DORT: Modeling Dynamic Objects in Recurrent for Multi-Camera 3D Object Detection and Tracking

MMSI-Video-Bench: A Holistic Benchmark for Video-Based Spatial Intelligence

VL-LN Bench: Towards Long-horizon Goal-oriented Navigation with Active Dialogs

[ECCV2026] Official open-source repository for REAL——Exploratory, Communicative, and Deployable: Vision-Driven Embodied Agents for Open-World Mobile Manipulation

This is an official implementation of "HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit", including rl frameworkl, hardware system, and deployment.