{"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-transfer1-conditional-world-generation","title":"Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control","arxiv_id":"2503.14492","date":"2025-03-18","proceeding":null,"authors":["Nvidia",":","Hassan Abu Alhaija","Jose Alvarez","Maciej Bala","Tiffany Cai","Tianshi Cao","Liz Cha","Joshua Chen","Mike Chen","Francesco Ferroni","Sanja Fidler","Dieter Fox","Yunhao Ge","Jinwei Gu","Ali Hassani","Michael Isaev","Pooya Jannaty","Shiyi Lan","Tobias Lasser","Huan Ling","Ming-Yu Liu","Xian Liu","Yifan Lu","Alice Luo","Qianli Ma","Hanzi Mao","Fabio Ramos","Xuanchi Ren","Tianchang Shen","Xinglong Sun","Shitao Tang","Ting-Chun Wang","Jay Wu","Jiashu Xu","Stella Xu","Kevin Xie","Yuchong Ye","Xiaodong Yang","Xiaohui Zeng","Yu Zeng"],"abstract":"We introduce Cosmos-Transfer, a conditional world generation model that can generate world simulations based on multiple spatial control inputs of various modalities such as segmentation, depth, and edge. In the design, the spatial conditional scheme is adaptive and customizable. It allows weighting different conditional inputs differently at different spatial locations. This enables highly controllable world generation and finds use in various world-to-world transfer use cases, including Sim2Real. We conduct extensive evaluations to analyze the proposed model and demonstrate its applications for Physical AI, including robotics Sim2Real and autonomous vehicle data enrichment. We further demonstrate an inference scaling strategy to achieve real-time world generation with an NVIDIA GB200 NVL72 rack. To help accelerate research development in the field, we open-source our models and code at https://github.com/nvidia-cosmos/cosmos-transfer1.","url_abs":"https://arxiv.org/abs/2503.14492v2","url_pdf":"https://arxiv.org/pdf/2503.14492v2.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-transfer1-conditional-world-generation","repo_url":"https://github.com/nvidia-cosmos/cosmos-transfer1","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"cosmos-transfer1-conditional-world-generation","repo_url":"https://github.com/nv-tlabs/cosmos-drive-dreams","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.14492","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.14492"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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-transfer1","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nv-tlabs/cosmos-drive-dreams","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":15},"by_repo_kind":{"official":{"samples":2,"ran":0,"repositories":1},"listed":{"samples":13,"ran":0,"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":"a64dcc826fd7beed","entry":"analyze_traffic_light_with_clip","repo":"nv-tlabs/cosmos-drive-dreams","repo_kind":"listed","path":"cosmos-drive-dreams-toolkits/crop_traffic_lights.py","file_url":"https://github.com/nv-tlabs/cosmos-drive-dreams/blob/HEAD/cosmos-drive-dreams-toolkits/crop_traffic_lights.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":"a64dcc826fd7beed"}},{"code_sha256_prefix":"6b17f23178a2868f","entry":"broadcast_object","repo":"nvidia-cosmos/cosmos-transfer1","repo_kind":"official","path":"cosmos_transfer1/checkpointer/safe_broadcast.py","file_url":"https://github.com/nvidia-cosmos/cosmos-transfer1/blob/HEAD/cosmos_transfer1/checkpointer/safe_broadcast.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":"6b17f23178a2868f"}},{"code_sha256_prefix":"55d080a2eba4d6b7","entry":"calculate_metrics","repo":"nv-tlabs/cosmos-drive-dreams","repo_kind":"listed","path":"cosmos-drive-dreams-toolkits/train_light_model.py","file_url":"https://github.com/nv-tlabs/cosmos-drive-dreams/blob/HEAD/cosmos-drive-dreams-toolkits/train_light_model.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":"55d080a2eba4d6b7"}},{"code_sha256_prefix":"7e236dc4ecb21240","entry":"estimate_ground_height","repo":"nv-tlabs/cosmos-drive-dreams","repo_kind":"listed","path":"cosmos-drive-dreams-toolkits/visualize_rds_hq.py","file_url":"https://github.com/nv-tlabs/cosmos-drive-dreams/blob/HEAD/cosmos-drive-dreams-toolkits/visualize_rds_hq.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":"7e236dc4ecb21240"}},{"code_sha256_prefix":"af33c328c499d24b","entry":"extract_clip_id_from_image_name","repo":"nv-tlabs/cosmos-drive-dreams","repo_kind":"listed","path":"cosmos-drive-dreams-toolkits/crop_traffic_lights_for_training.py","file_url":"https://github.com/nv-tlabs/cosmos-drive-dreams/blob/HEAD/cosmos-drive-dreams-toolkits/crop_traffic_lights_for_training.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":"af33c328c499d24b"}},{"code_sha256_prefix":"574a2f62de49c221","entry":"get_nearest_lidar_indices","repo":"nv-tlabs/cosmos-drive-dreams","repo_kind":"listed","path":"cosmos-drive-dreams-toolkits/render_from_rds_hq.py","file_url":"https://github.com/nv-tlabs/cosmos-drive-dreams/blob/HEAD/cosmos-drive-dreams-toolkits/render_from_rds_hq.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":"574a2f62de49c221"}},{"code_sha256_prefix":"14680804773f0813","entry":"get_rectification_image_grid","repo":"nv-tlabs/cosmos-drive-dreams","repo_kind":"listed","path":"cosmos-drive-dreams-toolkits/rectify_ftheta_to_pinhole.py","file_url":"https://github.com/nv-tlabs/cosmos-drive-dreams/blob/HEAD/cosmos-drive-dreams-toolkits/rectify_ftheta_to_pinhole.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":"14680804773f0813"}},{"code_sha256_prefix":"39b2df8191427550","entry":"grounding_pose","repo":"nv-tlabs/cosmos-drive-dreams","repo_kind":"listed","path":"cosmos-drive-dreams-toolkits/visualize_rds_hq.py","file_url":"https://github.com/nv-tlabs/cosmos-drive-dreams/blob/HEAD/cosmos-drive-dreams-toolkits/visualize_rds_hq.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":"39b2df8191427550"}},{"code_sha256_prefix":"0bf9492cb31ff028","entry":"interpolate_pose","repo":"nv-tlabs/cosmos-drive-dreams","repo_kind":"listed","path":"cosmos-drive-dreams-toolkits/utils/bbox_utils.py","file_url":"https://github.com/nv-tlabs/cosmos-drive-dreams/blob/HEAD/cosmos-drive-dreams-toolkits/utils/bbox_utils.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":"0bf9492cb31ff028"}},{"code_sha256_prefix":"2f19456eeaab8957","entry":"load_clip_model","repo":"nv-tlabs/cosmos-drive-dreams","repo_kind":"listed","path":"cosmos-drive-dreams-toolkits/crop_traffic_lights.py","file_url":"https://github.com/nv-tlabs/cosmos-drive-dreams/blob/HEAD/cosmos-drive-dreams-toolkits/crop_traffic_lights.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":"2f19456eeaab8957"}},{"code_sha256_prefix":"6e674ab7a391a0d2","entry":"load_qwen_model","repo":"nv-tlabs/cosmos-drive-dreams","repo_kind":"listed","path":"cosmos-drive-dreams-toolkits/crop_traffic_lights.py","file_url":"https://github.com/nv-tlabs/cosmos-drive-dreams/blob/HEAD/cosmos-drive-dreams-toolkits/crop_traffic_lights.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":"6e674ab7a391a0d2"}},{"code_sha256_prefix":"7e675e35b8ade959","entry":"quaternion_uniform_flip","repo":"nv-tlabs/cosmos-drive-dreams","repo_kind":"listed","path":"cosmos-drive-dreams-toolkits/utils/animation_utils.py","file_url":"https://github.com/nv-tlabs/cosmos-drive-dreams/blob/HEAD/cosmos-drive-dreams-toolkits/utils/animation_utils.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":"7e675e35b8ade959"}},{"code_sha256_prefix":"00c0672f3febbf9f","entry":"scatter_full_optim_state_dict","repo":"nvidia-cosmos/cosmos-transfer1","repo_kind":"official","path":"cosmos_transfer1/checkpointer/fsdp_optim_fix.py","file_url":"https://github.com/nvidia-cosmos/cosmos-transfer1/blob/HEAD/cosmos_transfer1/checkpointer/fsdp_optim_fix.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":"00c0672f3febbf9f"}},{"code_sha256_prefix":"8381210aed1abe7f","entry":"simple_confusion_matrix","repo":"nv-tlabs/cosmos-drive-dreams","repo_kind":"listed","path":"cosmos-drive-dreams-toolkits/train_light_model.py","file_url":"https://github.com/nv-tlabs/cosmos-drive-dreams/blob/HEAD/cosmos-drive-dreams-toolkits/train_light_model.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":"8381210aed1abe7f"}},{"code_sha256_prefix":"c7633667302f3088","entry":"simple_train_test_split","repo":"nv-tlabs/cosmos-drive-dreams","repo_kind":"listed","path":"cosmos-drive-dreams-toolkits/train_light_model.py","file_url":"https://github.com/nv-tlabs/cosmos-drive-dreams/blob/HEAD/cosmos-drive-dreams-toolkits/train_light_model.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":"c7633667302f3088"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}