mlsanityData to 7 Oct 2026

World Simulation with Video Foundation Models for Physical AI

arXiv 2511.00062 ↗First posted 28 Oct 2025cs.CV cs.AI cs.LGcited by 183

Not on the map. Why?

Cited by 102 in World models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We introduce [Cosmos-Predict2.5], the latest generation of the Cosmos World Foundation Models for Physical AI. Built on a flow-based architecture, [Cosmos-Predict2.5] unifies Text2World, Image2World, and Video2World generation in a single model and leverages [Cosmos-Reason1], a Physical AI vision-language model, to provide richer text grounding and finer control of world simulation. Trained on 200M curated video clips and refined with reinforcement learning-based post-training, [Cosmos-Predict2.5] achieves substantial improvements over [Cosmos-Predict1] in video quality and instruction alignment, with models released at 2B and 14B scales. These capabilities enable more reliable synthetic data generation, policy evaluation, and closed-loop simulation for robotics and autonomous systems. We further extend the family with [Cosmos-Transfer2.5], a control-net style framework for Sim2Real and Real2Real world translation. Despite being 3.5× smaller than [Cosmos-Transfer1], it delivers higher fidelity and robust long-horizon video generation. Together, these advances establish [Cosmos-Predict2.5] and [Cosmos-Transfer2.5] as versatile tools for scaling embodied intelligence. To accelerate research and deployment in Physical AI, we release source code, pretrained checkpoints, and curated benchmarks under the NVIDIA Open Model License at https://github.com/nvidia-cosmos/cosmos-predict2.5 and https://github.com/nvidia-cosmos/cosmos-transfer2.5. We hope these open resources lower the barrier to adoption and foster innovation in building the next generation of embodied intelligence.

Key facts. Cited by 183 papers in the map (data through 7 Oct 2026). Builds on 84 of its 96 references that are in the map. First posted on arXiv 28 Oct 2025.

Builds on

84 of 96 references.

References · 84

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  4. 2022Flow Matching for Generative Modelingcited by 5,426
  5. 2025Qwen2.5-VL Technical Reportcited by 5,418
  6. 2024GPT-4o System Cardcited by 4,467
  7. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  8. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  9. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  10. 2024SAM 2: Segment Anything in Images and Videoscited by 2,784
  11. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  12. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,536
38 more
  1. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,198
  2. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,598
  3. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,597
  4. 2018World Modelscited by 1,444
  5. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,366
  6. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  7. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,167
  8. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  9. 2024Grounded SAM: Assembling Open-World Models for Diverse Visual Taskscited by 914
  10. 2025Cosmos World Foundation Model Platform for Physical AIcited by 833
  11. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 801
  12. 2023TIES-Merging: Resolving Interference When Merging Modelscited by 795
  13. 2025V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planningcited by 738
  14. 2023Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunchcited by 679
  15. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 634
  16. 2024Movie Gen: A Cast of Media Foundation Modelscited by 614
  17. 2023YaRN: Efficient Context Window Extension of Large Language Modelscited by 584
  18. 2024LTX-Video: Realtime Video Latent Diffusioncited by 549
  19. 2023Simple diffusion: End-to-end diffusion for high resolution imagescited by 413
  20. 2024RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robotscited by 391
  21. 2025AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systemscited by 390
  22. 2021Light Field Networks: Neural Scene Representations with Single-Evaluation Renderingcited by 330
  23. 2025GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Controlcited by 325
  24. 2022Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectivescited by 314
  25. 2024InternVideo2: Scaling Foundation Models for Multimodal Video Understandingcited by 310
  26. 2021StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2cited by 300
  27. 2025ReCamMaster: Camera-Controlled Generative Rendering from A Single Videocited by 278
  28. 2024Simplifying, Stabilizing and Scaling Continuous-Time Consistency Modelscited by 276
  29. 2025Improving Video Generation with Human Feedbackcited by 267
  30. 2024Diffusion Policy Policy Optimizationcited by 255
  31. 2024Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunitiescited by 247
  32. 2025Seedance 1.0: Exploring the Boundaries of Video Generation Modelscited by 247
  33. 2024VideoPhy: Evaluating Physical Commonsense for Video Generationcited by 215
  34. 2025EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agentscited by 213
  35. 2023Text-To-4D Dynamic Scene Generationcited by 204
  36. 2025Video Depth Anything: Consistent Depth Estimation for Super-Long Videoscited by 202
  37. 2023On the Importance of Noise Scheduling for Diffusion Modelscited by 193
  38. 2023RTMPose: Real-Time Multi-Person Pose Estimation based on MMPosecited by 170

50 most cited of 84 All 84 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 12; 2026: 171.

183 papers.

Sort:

By area:

  1. 2026World Action Models are Zero-shot Policiescited by 411
  2. 2026Advancing Open-source World Modelscited by 144
  3. 2026Cosmos 3: Omnimodal World Models for Physical AIcited by 137
  4. 2025mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAscited by 133
  5. 2026DreamDojo: A Generalist Robot World Model from Large-Scale Human Videoscited by 117
  6. 2026DiT4DiT: Jointly Modeling Video Dynamics and Actions for Generalizable Robot Controlcited by 71
  7. 2025GigaWorld-0: World Models as Data Engine to Empower Embodied AIcited by 60
  8. 2025DriveLaW:Unifying Planning and Video Generation in a Latent Driving Worldcited by 43
  9. 2026World Model for Robot Learning: A Comprehensive Surveycited by 42
  10. 2026Solaris: Building a Multiplayer Video World Model in Minecraftcited by 38
  11. 2026Do World Action Models Generalize Better than VLAs? A Robustness Studycited by 35
  12. 2025PAI-Bench: A Comprehensive Benchmark For Physical AIcited by 30
38 more
  1. 2026Rethinking Video Generation Model for the Embodied Worldcited by 30
  2. 2025SRPO: Self-Referential Policy Optimization for Vision-Language-Action Modelscited by 25
  3. 2026RLDX-1 Technical Reportcited by 25
  4. 2026Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Modelscited by 23
  5. 2026WorldCompass: Reinforcement Learning for Long-Horizon World Modelscited by 22
  6. 2026Qwen-AgentWorld: Language World Models for General Agentscited by 22
  7. 2025AstraNav-World: World Model for Foresight Control and Consistencycited by 17
  8. 2026Dream-Tac: A Unified Tactile World Action Model for Contact-Rich Robot Manipulationcited by 17
  9. 2026RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulationcited by 15
  10. 2026Self-Refining Video Samplingcited by 14
  11. 2026NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulationcited by 14
  12. 2025Data-regularized Reinforcement Learning for Diffusion Models at Scalecited by 13
  13. 2025BAgger: Backwards Aggregation for Mitigating Drift in Autoregressive Video Diffusion Modelscited by 13
  14. 2026CycleVLA: Proactive Self-Correcting Vision-Language-Action Models via Subtask Backtracking and Minimum Bayes Risk Decodingcited by 13
  15. 2026AnyView: Synthesizing Any Novel View in Dynamic Scenescited by 12
  16. 2026WorldBench: Benchmarking Physical Understanding of World Models by Isolating Physics Conceptscited by 12
  17. 2026ReRoPE: Repurposing RoPE for Relative Camera Controlcited by 12
  18. 2026When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoningcited by 12
  19. 2026VGGT-World: Transforming VGGT into an Autoregressive Geometry World Modelcited by 11
  20. 2026Action Images: End-to-End Policy Learning via Multiview Video Generationcited by 10
  21. 2026Is the Future Compatible? Diagnosing Dynamic Consistency in World Action Modelscited by 10
  22. 2026NEWTON: Agentic Planning for Physically Grounded Video Generationcited by 10
  23. 2026Gamma-World: Generative Multi-Agent World Modeling Beyond Two Playerscited by 10
  24. 2026Metis: A Generalizable and Efficient World-Action Model for Autonomous Driving and Urban Navigationcited by 10
  25. 2026FlowWAM: Optical Flow as a Unified Action Representation for World Action Modelscited by 10
  26. 2026Plenoptic Video Generationcited by 9
  27. 2026UniDriveDreamer: A Single-Stage Multimodal World Model for Autonomous Drivingcited by 9
  28. 2026NavDreamer: Video Models as Zero-Shot 3D Navigatorscited by 9
  29. 2026AdaWorldPolicy: World-Model-Driven Diffusion Policy with Online Adaptive Learning for Robotic Manipulationcited by 9
  30. 2026MemoryVLA++: Temporal Modeling via Memory and Imagination in Vision-Language-Action Modelscited by 9
  31. 2026RepWAM: World Action Modeling with Representation Visual-Action Tokenizerscited by 9
  32. 2026How Should World Models Be Evaluated for Embodied Decision-Making? A Decision-Making-Centric Positioncited by 9
  33. 2026Coarse-to-Real: Generative Rendering for Populated Dynamic Scenescited by 8
  34. 2026WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platformcited by 8
  35. 2026MotionWAM: Towards Foundation World Action Models for Real-Time Humanoid Loco-Manipulationcited by 8
  36. 2026Prisma-World: Camera-Controllable Multi-Agent Video World Modelcited by 8
  37. 2026RoboCurate: Harnessing Diversity with Action-Verified Neural Trajectory for Robot Learningcited by 7
  38. 2026The Pulse of Motion: Measuring Physical Frame Rate from Visual Dynamicscited by 7

50 most cited of 183 All 183 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning
  2. 2025Simulating the Visual World with Artificial Intelligence: A Roadmap
  3. 2024Pandora: Towards General World Model with Natural Language Actions and Video States
  4. 2026From Generation to Simulation: How Far Are World Models from Being True Simulators?
  5. 2025Adapting Vision-Language Models for Evaluating World Models
  6. 2025Dreamland: Controllable World Creation with Simulator and Generative Models
  7. 2026Efficient Sim-to-Real Transfer of World-Action Models from Synthetic Priors
  8. 2026Robotic Video World Models: A Survey of Applications, Research Challenges, Future Directions