OpenRobotLab

[ECCV 2024 Oral] PointLLM: Empowering Large Language Models to Understand Point Clouds

OpenRobotLab

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

OpenRobotLab

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

OpenRobotLab

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

OpenRobotLab

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

OpenRobotLab

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

OpenRobotLab

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

InternRobotics

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

InternRobotics

G2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning

InternRobotics

InternRobotics' open platform for building generalized navigation foundation models.

InternRobotics