PyTorch code and models for VJEPA2 self-supervised learning from video.
☆4,765Mar 23, 2026Updated 6 months ago
Alternatives and similar repositories for vjepa2
Users that are interested in vjepa2 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals☆2,702Apr 19, 2026Updated 5 months ago
- Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels☆4,525May 26, 2026Updated 4 months ago
- Reference PyTorch implementation and models for DINOv3☆11,543Jul 15, 2026Updated 2 months ago
- [RSS 2026] Causal video-action world model for generalist robot control☆1,934Jul 9, 2026Updated 3 months ago
- Official codebase for Fast-WAM: Do World Action Models Need Test-time Future Imagination?☆1,573Aug 20, 2026Updated last month
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Cosmos Policy☆888Jan 23, 2026Updated 8 months ago
- ☆14,229Aug 24, 2026Updated last month
- Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the …☆1,379Jun 8, 2026Updated 4 months ago
- Official Codebase for "DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos" (ICML 2026)☆1,117Mar 21, 2026Updated 6 months ago
- ☆594Mar 24, 2025Updated last year
- State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!☆2,382Apr 13, 2026Updated 6 months ago
- NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomou …☆12,035Updated this week
- DreamGen: Nvidia GEAR Lab's initiative to solve the robotics data problem using world models☆621Oct 24, 2025Updated 11 months ago
- NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.☆8,204Oct 7, 2026Updated last week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- OpenVLA: An open-source vision-language-action model for robotic manipulation.☆7,147Mar 23, 2025Updated last year
- Official code of Motus: A Unified Latent Action World Model☆1,310Updated this week
- StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing☆3,811Oct 8, 2026Updated last week
- Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"☆2,053Feb 25, 2026Updated 7 months ago
- A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts…☆3,474Updated this week
- Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world m…☆792Oct 29, 2025Updated 11 months ago
- [RSS 2025] Learning to Act Anywhere with Task-centric Latent Actions☆1,140Nov 19, 2025Updated 10 months ago
- Code, data and weights for the paper **What drives success in physical planning with Joint-Embedding Predictive World Models?**☆502Apr 11, 2026Updated 6 months ago
- [ECCV 2026] VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model☆611Sep 29, 2026Updated 2 weeks ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- [CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer☆14,506May 19, 2026Updated 4 months ago
- ICLR 2026 Paper: Ctrl-World☆569Apr 8, 2026Updated 6 months ago
- ☆1,390Jan 25, 2026Updated 8 months ago
- [ICLR 2025] LAPA: Latent Action Pretraining from Videos☆580Jan 22, 2025Updated last year
- RynnVLA-002: A Unified Vision-Language-Action and World Model☆1,139Dec 2, 2025Updated 10 months ago
- [ICLR 2026] π^3: Permutation-Equivariant Visual Geometry Learning☆2,211Jul 3, 2026Updated 3 months ago
- Depth Anything 3☆6,484Jul 27, 2026Updated 2 months ago
- Benchmarking Knowledge Transfer in Lifelong Robot Learning☆2,418Mar 15, 2025Updated last year
- Native Multimodal Models are World Learners☆1,562Dec 30, 2025Updated 9 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Official code for the CVPR 2025 paper "Navigation World Models".☆698Nov 24, 2025Updated 10 months ago
- Official PyTorch Implementation of Unified Video Action Model (RSS 2025)☆415Aug 21, 2026Updated last month
- Advancing Open-source World Models☆4,527Jul 9, 2026Updated 3 months ago
- A Large-scale Video Action Dataset☆494Jan 16, 2026Updated 8 months ago
- A comprehensive list of papers for the definition of World Models and using World Models for General Video Generation, Embodied AI, and A…☆2,038Updated this week
- Self-supervised learning for spatial perception☆986Jul 8, 2026Updated 3 months ago
- [ICLR 2026] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning☆1,884Jan 6, 2026Updated 9 months ago