Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.
☆792Oct 29, 2025Updated last year
Alternatives and similar repositories for cosmos-predict2
Users that are interested in cosmos-predict2 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the …☆1,394Jun 8, 2026Updated 5 months ago
- Cosmos-Predict1 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world m…☆476Oct 15, 2026Updated 3 weeks ago
- Cosmos-Transfer1 is a world-to-world transfer model designed to bridge the perceptual divide between simulated and real-world environment…☆830Oct 15, 2026Updated 3 weeks ago
- DreamGen: Nvidia GEAR Lab's initiative to solve the robotics data problem using world models☆629Oct 24, 2025Updated last year
- Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long c…☆962Jun 7, 2026Updated 5 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Cosmos Policy☆897Jan 23, 2026Updated 9 months ago
- Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control in…☆763Jun 30, 2026Updated 4 months ago
- Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals☆2,761Apr 19, 2026Updated 6 months ago
- Official PyTorch Implementation of Unified Video Action Model (RSS 2025)☆417Aug 21, 2026Updated 2 months ago
- NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomou…☆12,324Updated this week
- Cosmos Curator is a toolkit for curating physical AI training data.☆305Oct 16, 2026Updated 3 weeks ago
- Cosmos-RL is a flexible and scalable Reinforcement Learning framework specialized for Physical AI applications.☆485Oct 22, 2026Updated 2 weeks ago
- PyTorch code and models for VJEPA2 self-supervised learning from video.☆4,864Oct 29, 2026Updated last week
- [RSS 2026] Causal video-action world model for generalist robot control☆1,978Jul 9, 2026Updated 4 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ICCV 2025 | TesserAct: Learning 4D Embodied World Models☆412Aug 4, 2025Updated last year
- [CVPR 2025 Highlight] GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control☆1,450Jun 15, 2026Updated 4 months ago
- ☆592Sep 10, 2026Updated last month
- Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)☆3,562Sep 12, 2025Updated last year
- ViPE: Video Pose Engine for Geometric 3D Perception☆2,194Updated this week
- [RSS 2025] Learning to Act Anywhere with Task-centric Latent Actions☆1,145Nov 19, 2025Updated 11 months ago
- RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots☆1,872Oct 30, 2026Updated last week
- A suite of image and video neural tokenizers☆1,727Feb 11, 2025Updated last year
- Official Codebase for "DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos" (ICML 2026)☆1,130Mar 21, 2026Updated 7 months ago
- 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.
- [ICCV 2025 & ICCV 2025 RIWM Outstanding Paper] Aether: Geometric-Aware Unified World Modeling☆617Oct 26, 2025Updated last year
- Official code of RDT 2☆810Feb 7, 2026Updated 9 months ago
- [ICLR’26] Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Control☆108Feb 8, 2026Updated 9 months ago
- ICLR 2026 Paper: Ctrl-World☆583Apr 8, 2026Updated 7 months ago
- HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency☆1,626Jun 10, 2026Updated 4 months ago
- (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models☆1,455Aug 7, 2025Updated last year
- Unfied World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets☆259Oct 8, 2025Updated last year
- [SIGGRAPH 2025] Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control☆851Jun 9, 2025Updated last year
- [ICLR 2026] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling☆506Apr 16, 2026Updated 6 months ago
- 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.
- [CVPR 2026] SpatialVID: A Large-Scale Video Dataset with Spatial Annotations☆614Apr 22, 2026Updated 6 months ago
- [IROS 2025 Best Paper Award Finalist & IEEE TRO 2026] The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems☆3,228May 29, 2026Updated 5 months ago
- [NeurIPS 2025] WorldMem: Long-term Consistent World Simulation with Memory☆404Feb 21, 2026Updated 8 months ago
- [ICCV 2025] GameFactory: Creating New Games with Generative Interactive Videos☆502Mar 22, 2025Updated last year
- Cambrian-S: Towards Spatial Supersensing in Video☆573Apr 3, 2026Updated 7 months ago
- Official repo for vidar and vidarc: video foundation model for robotics.☆44Dec 22, 2025Updated 10 months ago
- Official code of Motus: A Unified Latent Action World Model☆1,316Oct 9, 2026Updated last month
Are these results useful?