[ICLR 2025 (Oral 📢) ] Our OpenYOLO3D model achieves state-of-the-art performance in Open Vocabulary 3D Instance Segmentation on ScanNet200 and Replica datasets with up ∼16x speedup compared to the …

🔥[ICLR'25] LLaRA: Supercharging Robot Learning Data for Vision-Language Policy

[ECCV 2024] SGS-SLAM: Semantic Gaussian Splatting For Neural Dense SLAM

SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding

An open source implementation of CLIP.

This is the official repository for "EgoLifter Open-world 3D Segmentation for Egocentric Perception, ECCV 2024"

[CVPR'23] Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAM

DUSt3R: Geometric 3D Vision Made Easy

Remote web teleoperation for the Stretch mobile manipulators from Hello Robot Inc.

Dimensionality reduction in very large datasets using Siamese Networks

GaussianRoom Repo

code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"

[CVPR'24] Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial Imagery

[ICLR 2025 Spotlight] MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility

[CoRL 2024] Open-TeleVision: Teleoperation with Immersive Active Visual Feedback

PIPs++

A Modular Framework for 3D Gaussian Splatting and Beyond

OpenVLA: An open-source vision-language-action model for robotic manipulation.

Level of Gaussians

[RAL 2024] OpenGraphs: Open-Vocabulary Hierarchical 3D Scene Graphs in Large-Scale Outdoor Environments