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.
☆746Oct 29, 2025Updated 4 months ago
Alternatives and similar repositories for cosmos-predict2
Users that are interested in cosmos-predict2 are comparing it to the libraries listed below
Sorting:
- Cosmos-Transfer1 is a world-to-world transfer model designed to bridge the perceptual divide between simulated and real-world environment…☆779Jan 6, 2026Updated 2 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…☆414Jan 6, 2026Updated 2 months ago
- Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long c…☆920Jan 6, 2026Updated 2 months ago
- DreamGen: Nvidia GEAR Lab's initiative to solve the robotics data problem using world models☆486Oct 24, 2025Updated 4 months ago
- [CVPR 2025 Highlight] GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control☆1,271Sep 24, 2025Updated 5 months ago
- Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the …☆860Feb 24, 2026Updated last week
- [ICLR 2026] Codebase for paper "Geometry-aware 4D Video Generation for Robot Manipulation"☆88Jan 10, 2026Updated last month
- [ICLR’26] Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Control☆99Feb 8, 2026Updated 3 weeks ago
- A suite of image and video neural tokenizers☆1,711Feb 11, 2025Updated last year
- Cosmos-Curate is a powerful video curation system that processes, analyzes, and organizes video content using advanced AI models and dist…☆153Jan 9, 2026Updated last month
- [SIGGRAPH 2025] Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control☆808Jun 9, 2025Updated 8 months ago
- [T-PAMI 2025] V3D: Video Diffusion Models are Effective 3D Generators☆518Mar 26, 2024Updated last year
- [ICCV 2025] DSO: Aligning 3D Generators with Simulation Feedback for Physical Soundness☆175Feb 11, 2026Updated 3 weeks ago
- [ICCV 2025 & ICCV 2025 RIWM Outstanding Paper] Aether: Geometric-Aware Unified World Modeling☆575Oct 26, 2025Updated 4 months ago
- Code for ICCV'2025 (Best student paper honorable mention) "RayZer: A Self-supervised Large View Synthesis Model"☆415Nov 24, 2025Updated 3 months ago
- Official code for NeurIPS 2024 paper LRM-Zero: Training Large Reconstruction Models with Synthesized Data☆153Oct 7, 2024Updated last year
- Official PyTorch Implementation of Unified Video Action Model (RSS 2025)☆338Jul 23, 2025Updated 7 months ago
- Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models☆427Dec 8, 2025Updated 2 months ago
- Official Implementation of paper "MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"☆1,337Jun 16, 2025Updated 8 months ago
- New repo collection for NVIDIA Cosmos: https://github.com/nvidia-cosmos☆8,082Jan 6, 2026Updated 2 months ago
- (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models☆1,232Aug 7, 2025Updated 7 months ago
- Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals☆1,033Updated this week
- News: the 10k dataset is ready for download.☆575Feb 10, 2026Updated 3 weeks ago
- [TPAMI 2025] ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis☆1,518Dec 13, 2025Updated 2 months ago
- Official implementation of Continuous 3D Perception Model with Persistent State☆1,345Aug 27, 2025Updated 6 months ago
- PyTorch code and models for VJEPA2 self-supervised learning from video.☆3,059Aug 28, 2025Updated 6 months ago
- Distributed Robot Interaction Dataset.☆326Sep 15, 2025Updated 5 months ago
- [ICCV 2025, Oral] TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models☆839Dec 17, 2025Updated 2 months ago
- [ICLR 2026] Streaming 4D Visual Geometry Transformer☆832Oct 27, 2025Updated 4 months ago
- Official Repo for Self-Forcing++ High Quality Long Video Generation☆241Oct 13, 2025Updated 4 months ago
- A unified inference and post-training framework for accelerated video generation.☆3,111Feb 28, 2026Updated last week
- Lightplane implements a highly memory-efficient differentiable radiance field renderer, and a module for unprojecting features from image…☆285Aug 6, 2024Updated last year
- Official repository of Learning to Act from Actionless Videos through Dense Correspondences.☆249Apr 25, 2024Updated last year
- ICCV 2025 | TesserAct: Learning 4D Embodied World Models☆380Aug 4, 2025Updated 7 months ago
- ☆94Sep 4, 2024Updated last year
- [ICLR 2026] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling☆433Feb 25, 2026Updated last week
- MAGI-1: Autoregressive Video Generation at Scale☆3,647Jun 17, 2025Updated 8 months ago
- [CVPR 2026] SpatialVID: A Large-Scale Video Dataset with Spatial Annotations☆504Updated this week
- Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)☆3,180Sep 12, 2025Updated 5 months ago