MapAnything: Universal Feed-Forward Metric 3D Reconstruction

Official code of Motus: A Unified Latent Action World Model

The offical Implementation of "Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model"

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

EO: Open-source Unified Embodied Foundation Model Series

EO: Open-source Unified Embodied Foundation Model Series

[ICCV2025 Oral] Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos

Taming Transformers for High-Resolution Image Synthesis

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

Visual Spatial Tuning

[NeurIPS 2025] Pixel-Perfect Depth

[IROS 2025 Award Finalist] The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems

NEO Series: Native Vision-Language Models from First Principles

Unified Vision-Language-Action Model

Official implementation of Spatial-Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model

A curated list of state-of-the-art research in embodied AI, focusing on vision-language-action (VLA) models, vision-language navigation (VLN), and related multimodal learning approaches.

This is the code for Deformable Neural Radiance Fields, a.k.a. Nerfies.

A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/

Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success

A Simple, Modular and Unified Real Robot Control Interface

PyTorch code and models for the DINOv2 self-supervised learning method.

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

PyTorch implementation of Pointnet2/Pointnet++. Upgraded to fit the latest cuda version

PyTorch implementation of Pointnet2/Pointnet++

[RSS 2024] 3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations

[CVPR 2023 Highlight] Perspective Fields for Single Image Camera Calibration