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.
☆794Oct 29, 2025Updated 8 months ago
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 …☆1,335Jun 8, 2026Updated last month
- Cosmos-Predict1 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world m…☆465Jun 7, 2026Updated last month
- Cosmos-Transfer1 is a world-to-world transfer model designed to bridge the perceptual divide between simulated and real-world environment…☆811Jun 7, 2026Updated last month
- DreamGen: Nvidia GEAR Lab's initiative to solve the robotics data problem using world models☆591Oct 24, 2025Updated 9 months ago
- Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long c…☆952Jun 7, 2026Updated last month
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Cosmos Policy☆837Jan 23, 2026Updated 6 months ago
- Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control in…☆710Jun 30, 2026Updated 3 weeks ago
- Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals☆2,484Apr 19, 2026Updated 3 months ago
- Cosmos Curator is a powerful video curation system that processes, analyzes, and organizes video content using advanced AI models and dis…☆236Jun 11, 2026Updated last month
- Official PyTorch Implementation of Unified Video Action Model (RSS 2025)☆400Jul 23, 2025Updated last year
- PyTorch code and models for VJEPA2 self-supervised learning from video.☆4,401Mar 23, 2026Updated 4 months ago
- [RSS 2026] Causal video-action world model for generalist robot control☆1,686Jul 9, 2026Updated 2 weeks ago
- NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomou…☆11,249Updated this week
- Cosmos-RL is a flexible and scalable Reinforcement Learning framework specialized for Physical AI applications.☆466Updated this week
- 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.
- ☆564Jun 24, 2026Updated last month
- [CVPR 2025 Highlight] GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control☆1,389Jun 15, 2026Updated last month
- ICCV 2025 | TesserAct: Learning 4D Embodied World Models☆403Aug 4, 2025Updated 11 months ago
- [RSS 2025] Learning to Act Anywhere with Task-centric Latent Actions☆1,115Nov 19, 2025Updated 8 months ago
- Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)☆3,464Sep 12, 2025Updated 10 months ago
- ViPE: Video Pose Engine for Geometric 3D Perception☆2,052Jun 9, 2026Updated last month
- RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots☆1,580Jul 8, 2026Updated 2 weeks ago
- Official Codebase for "DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos" (ICML 2026)☆1,013Mar 21, 2026Updated 4 months ago
- [ICCV 2025 & ICCV 2025 RIWM Outstanding Paper] Aether: Geometric-Aware Unified World Modeling☆604Oct 26, 2025Updated 9 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.
- [ICLR’26] Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Control☆107Feb 8, 2026Updated 5 months ago
- (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models☆1,409Aug 7, 2025Updated 11 months ago
- HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency☆1,562Jun 10, 2026Updated last month
- Official code of RDT 2☆795Feb 7, 2026Updated 5 months ago
- ICLR 2026 Paper: Ctrl-World☆538Apr 8, 2026Updated 3 months ago
- [ICLR 2026] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling☆485Apr 16, 2026Updated 3 months ago
- A suite of image and video neural tokenizers☆1,732Feb 11, 2025Updated last year
- Official code of Motus: A Unified Latent Action World Model☆1,213Jan 5, 2026Updated 6 months ago
- [NeurIPS 2025] WorldMem: Long-term Consistent World Simulation with Memory☆381Feb 21, 2026Updated 5 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.
- [ICLR 2025] LAPA: Latent Action Pretraining from Videos☆560Jan 22, 2025Updated last year
- Unfied World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets☆246Oct 8, 2025Updated 9 months ago
- [IROS 2025 Best Paper Award Finalist & IEEE TRO 2026] The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems☆3,107May 29, 2026Updated last month
- [ICML 2025] Official PyTorch Implementation of "History-Guided Video Diffusion"☆705Jul 1, 2025Updated last year
- Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory☆2,278Mar 30, 2026Updated 3 months ago
- Official repo for vidar and vidarc: video foundation model for robotics.☆42Dec 22, 2025Updated 7 months ago
- [ICCV 2025] GameFactory: Creating New Games with Generative Interactive Videos☆492Mar 22, 2025Updated last year