{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/cosmos-reason1-from-physical-common-sense-to","title":"Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning","arxiv_id":"2503.15558","date":"2025-03-18","proceeding":null,"authors":["Nvidia",":","Alisson Azzolini","Junjie Bai","Hannah Brandon","Jiaxin Cao","Prithvijit Chattopadhyay","Huayu Chen","Jinju Chu","Yin Cui","Jenna Diamond","Yifan Ding","Liang Feng","Francesco Ferroni","Rama Govindaraju","Jinwei Gu","Siddharth Gururani","Imad El Hanafi","Zekun Hao","Jacob Huffman","Jingyi Jin","Brendan Johnson","Rizwan Khan","George Kurian","Elena Lantz","Nayeon Lee","Zhaoshuo Li","Xuan Li","Maosheng Liao","Tsung-Yi Lin","Yen-Chen Lin","Ming-Yu Liu","Xiangyu Lu","Alice Luo","Andrew Mathau","Yun Ni","Lindsey Pavao","Wei Ping","David W. Romero","Misha Smelyanskiy","Shuran Song","Lyne Tchapmi","Andrew Z. Wang","Boxin Wang","Haoxiang Wang","Fangyin Wei","Jiashu Xu","Yao Xu","Dinghao Yang","Xiaodong Yang","Zhuolin Yang","Jingxu Zhang","Xiaohui Zeng","Zhe Zhang"],"abstract":"Physical AI systems need to perceive, understand, and perform complex actions in the physical world. In this paper, we present the Cosmos-Reason1 models that can understand the physical world and generate appropriate embodied decisions (e.g., next step action) in natural language through long chain-of-thought reasoning processes. We begin by defining key capabilities for Physical AI reasoning, with a focus on physical common sense and embodied reasoning. To represent physical common sense, we use a hierarchical ontology that captures fundamental knowledge about space, time, and physics. For embodied reasoning, we rely on a two-dimensional ontology that generalizes across different physical embodiments. Building on these capabilities, we develop two multimodal large language models, Cosmos-Reason1-7B and Cosmos-Reason1-56B. We curate data and train our models in two stages: Physical AI supervised fine-tuning (SFT) and Physical AI reinforcement learning (RL). To evaluate our models, we build comprehensive benchmarks for physical common sense and embodied reasoning according to our ontologies. Evaluation results show that Physical AI SFT and RL bring significant improvements. To facilitate the development of Physical AI, we make our code and pre-trained models available under the NVIDIA Open Model License at https://github.com/nvidia-cosmos/cosmos-reason1.","url_abs":"https://arxiv.org/abs/2503.15558v3","url_pdf":"https://arxiv.org/pdf/2503.15558v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"cosmos-reason1-from-physical-common-sense-to","repo_url":"https://github.com/nvidia-cosmos/cosmos-reason1","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"3d-face-animation","task_name":"3D Face Animation"},{"task_slug":"common-sense-reasoning","task_name":"Common Sense Reasoning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[{"method_slug":"focus","method_name":"Focus"},{"method_slug":"ontology","method_name":"Ontology"},{"method_slug":"sft","method_name":"SFT"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2503.15558","atlas_url":"https://app.syntology.ai/?focus=2503.15558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.15558"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nvidia-cosmos/cosmos-reason1","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"d5bbbb9d375320b0","entry":"extract_tagged_text","repo":"nvidia-cosmos/cosmos-reason1","repo_kind":"official","path":"cosmos_reason1_utils/src/cosmos_reason1_utils/text.py","file_url":"https://github.com/nvidia-cosmos/cosmos-reason1/blob/HEAD/cosmos_reason1_utils/src/cosmos_reason1_utils/text.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d5bbbb9d375320b0"}},{"code_sha256_prefix":"bcecde3a9754efab","entry":"overlay_text","repo":"nvidia-cosmos/cosmos-reason1","repo_kind":"official","path":"cosmos_reason1_utils/src/cosmos_reason1_utils/vision.py","file_url":"https://github.com/nvidia-cosmos/cosmos-reason1/blob/HEAD/cosmos_reason1_utils/src/cosmos_reason1_utils/vision.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bcecde3a9754efab"}},{"code_sha256_prefix":"6f6d5ae4540e16c1","entry":"overlay_text_on_tensor","repo":"nvidia-cosmos/cosmos-reason1","repo_kind":"official","path":"cosmos_reason1_utils/src/cosmos_reason1_utils/vision.py","file_url":"https://github.com/nvidia-cosmos/cosmos-reason1/blob/HEAD/cosmos_reason1_utils/src/cosmos_reason1_utils/vision.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6f6d5ae4540e16c1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}