Cosmos World Foundation Model Platform for Physical AI
NVIDIA, :, Niket Agarwal, Arslan Ali, Madhu Bala, Yogesh Balaji, E. N. Barker, Tiffany Cai, Prithvijit Chattopadhyay, Yongxin Chen, Yin Cui, Yifan Ding, Daniel Dworakowski, Jiaojiao Fan, Michele Fenzi, Francesco Ferroni, Sanja Fidler, Dieter Fox, Songwei Ge, Yunhao Ge, Jinwei Gu, Siddharth Gururani, Ethan He, Jiahui Huang, J. B. Huffman, Pooya Jannaty, Jingyi Jin, Seung Wook Kim, Gergely Klár, Grace Y. Lam, Shiyi Lan, Laura Leal-Taixé, Anqi Li, Zhaoshuo Li, Chen-Hsuan Lin, Tsung‐Yi Lin, Huan Ling, Mingyu Liu, Xian Liu, Ancheng Luo, Qianli Ma, Hanzi Mao, Kaichun Mo, Arsalan Mousavian, Seungjun Nah, Sriharsha Niverty, David M. Page, Despoina Paschalidou, Zamurrud Patel, Lindsey Pavao, Morteza Ramezanali, Fitsum A. Reda, Xiaowei Ren, Vasanth Rao Naik Sabavat, Ed Schmerling, Stella Shi, Bartosz Stefaniak, Shitao Tang, Lyne Tchapmi, Przemek Tredak, Wei‐Cheng Tseng, Jibin Varghese, Hao Wang, Haoxiang Wang, Heng Wang, Ting-Chun Wang, Fangyin Wei, Xinyue Wei, Jay Zhangjie Wu, Jiashu Xu, Wei Yang, Lin Yen-Chen, Xiaohui Zeng, Yu Zeng, Jing Zhang, Qinsheng Zhang, Yuxuan Zhang, Qingqing Zhao, Artur Zolkowski
No strong AI-core implementation/artifact signals were detected from current providers.
Physical AI needs to be trained digitally first. It needs a digital twin of itself, the policy model, and a digital twin of the world, the world model. In this paper, we present the Cosmos World Foundation Model Platform to help developers build customized world models for their Physical AI setups. We position a world foundation model as a general-purpose world model that can be fine-tuned into customized world model ...
s for downstream applications. Our platform covers a video curation pipeline, pre-trained world foundation models, examples of post-training of pre-trained world foundation models, and video tokenizers. To help Physical AI builders solve the most critical problems of our society, we make Cosmos open-source and our models open-weight with permissive licenses available via https://github.com/nvidia-cosmos/cosmos-predict1.
Results & Benchmarks
No concrete benchmark grounding is available yet. Treat the page as context or an implementation starting point only.
Physical AI needs to be trained digitally first.
Implementation Evidence Summary
Recommendation evidence is currently too limited for a maintained-repo choice. Use Implementation Status and Reproduction Path for a practical baseline plan.
Reproduction Risks
- Estimate is based on paper-only reproduction flow
Hardware Notes
Expect multi-day setup/compute for meaningful reproduction based on current guidance.
Evidence disclosure
Evidence graph: 2 refs, 1 links.
Utility signals: depth 45/100, grounding 58/100, status medium.
Implementation Status
There is no verified maintained implementation yet. Use this baseline plan to decide whether to prototype now or defer.
- No direct maintained implementation was found. Use the paper PDF and citation graph to design a baseline reproduction.
- Start from related paper: The Foundation of Criminal Responsibility.
- Track assumptions and missing details in an experiment log before coding.
Reproduction readiness
Hardware requirements
- Expect multi-day setup/compute for meaningful reproduction based on current guidance.
No verified implementation available
- · No maintained repository has been identified for this paper. Check adjacent implementations or HF artifacts below.
No benchmark numbers could be verified. You will not be able to validate reproduction correctness against published numbers.
Hugging Face artifacts
No trustworthy direct or curated related Hugging Face artifacts were found yet.
Continue with targeted Hugging Face searches derived from the paper title and method context:
Datasets
Spaces
Tip: start with models, then check datasets/spaces if you need evaluation data or demos.
Direct artifact matches are currently sparse. Use targeted Hugging Face searches to quickly locate candidate models, datasets, and demos.
Research context
9
Citations
0
References
Tasks
Cosmos (plant), Foundation (evidence), Engineering, Computer Science, Computer Networks and Communications, Physical Sciences
Methods
None detected
Domains
None detected
Evaluation & Human Feedback Data
Open this paper in HFEPX to review benchmark signals, evaluation modes, and human-feedback protocol context.
Open in HFEPXExplore Similar Papers
Jump to Paper2Code search queries derived from this paper's research context.
Related papers
-
Search on Paper2Code
The Foundation of Criminal Responsibility (2009) Semantic similarity
-
Search on Paper2Code
'Hekdesh'--The 'Israeli Foundation' (2012) Semantic similarity
-
Search on Paper2Code
COSMOS / MT : 객체 저장 시스템 COSMOS 를 위한 멀티프로세스 / 멀티쓰레드 모델의 설계 및 구현 (2001) Semantic similarity
-
Search on Paper2Code
Design and Calculation of Open-cut Foundation (2006) Semantic similarity
-
Search on Paper2Code
FORD FOUNDATION. Report of the Study for the Ford Foundation on Policy and Program. Pp. 139. Detroit, 1949. No price (1951) Semantic similarity
-
Search on Paper2Code
St Kitts: how to choose from the menu of foundation jurisdictions, a reality check (2009) Semantic similarity
Need human evaluators for your AI research? Scale annotation with expert AI Trainers.