facebookresearch / eb_jepaLinks
An open source library designed to provide community examples of Joint Embedding Predictive Architectures (JEPAs). It contains code and examples for learning representations from images, video, and action-conditioned video, as well as planning using JEPA-based models.
☆45Updated last week
Alternatives and similar repositories for eb_jepa
Users that are interested in eb_jepa are comparing it to the libraries listed below
Sorting:
- [CVPR 2025 Highlight] Towards Autonomous Micromobility through Scalable Urban Simulation☆162Updated 3 weeks ago
- ☆27Updated 3 weeks ago
- ☆178Updated last week
- [ICCV 2025] GLEAM: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scene☆163Updated last week
- ☆133Updated 3 months ago
- Code, data and weights for the paper **What drives success in physical planning with Joint-Embedding Predictive World Models?**☆111Updated 3 weeks ago
- This is the code repository for IntPhys 2, a video benchmark designed to evaluate the intuitive physics understanding of deep learning mo…☆93Updated 3 months ago
- [CVPR 25] Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation☆250Updated 4 months ago
- [NeurIPS 2025] Official Implementation of DINO-Foresight: Looking into the Future with DINO☆146Updated 2 months ago
- source code and trained models for DeFM (Depth Foundation Model)☆32Updated this week
- [NeurIPS 2025] Source codes for the paper "MindJourney: Test-Time Scaling with World Models for Spatial Reasoning"☆125Updated 2 months ago
- Official repository for LeLaN training and inference code☆130Updated last year
- [ICML'25] The PyTorch implementation of paper: "AdaWorld: Learning Adaptable World Models with Latent Actions".☆194Updated 7 months ago
- PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigators☆106Updated last year
- Code repository for "DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers"☆75Updated 3 months ago
- ☆362Updated 10 months ago
- [CoRL 2024] VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding☆129Updated 8 months ago
- A toolbox for real-to-sim reconstruction and robotic simulation☆189Updated last week
- Official Repo of From Masks to Worlds: A Hitchhiker’s Guide to World Models.☆68Updated 3 months ago
- This repository is the official implementation of our paper (From reactive to cognitive: brain-inspired spatial intelligence for embodied…☆72Updated 2 months ago
- Official code for the CVPR 2025 paper "Navigation World Models".☆523Updated 2 months ago
- Code implementation of the paper "World-in-World: World Models in a Closed-Loop World"☆124Updated last month
- Evo-0: Vision-Language-Action Model with Implicit Spatial Understanding.☆52Updated 2 months ago
- [CVPR 2025] Source codes for the paper "3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning"☆210Updated 3 months ago
- Describe Anything, Anywhere, at Any Moment (DAAAM), a novel approach to real-time, large-scale, spatio-temporal memory☆139Updated last month
- Implementation of Danijar's latest iteration for his Dreamer line of work☆158Updated this week
- Causal video-action world model for generalist robot control☆289Updated this week
- Official implementation for BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation☆102Updated 6 months ago
- ☆30Updated 2 weeks ago
- Unifying 2D and 3D Vision-Language Understanding☆119Updated 6 months ago