Papers › Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control

Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control

18 Mar 2025arXiv:2503.14492archive 2025-07-28

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

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.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 15 code samples harvested from 2 repositories linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 2 samples from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 13 samples from 1 repository, 13 ran (13 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

nvidia-cosmos/cosmos-transfer1 officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
nv-tlabs/cosmos-drive-dreams mentioned on GitHubpytorchApache-2.0Syntology: 13 samples, 13 ran (0 instrument-failed) · 0 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

15 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

14ran
1unverified

Licence: 0 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

nvidia-cosmos/cosmos-transfer1 official repository 2 samples, 1 ran (0 instrument-failed) · 1 unverified
broadcast_object cosmos_transfer1/checkpointer/safe_broadcast.py ran Apache-2.0 (permissive) · 6b17f23178a2868f · report fixture: signature obj:dict/0/?, src_rank:int/0/int, group:NoneType/0/?, device:device/0/? · returned dict · level recorded 2026-09-25
scatter_full_optim_state_dict cosmos_transfer1/checkpointer/fsdp_optim_fix.py unverified Apache-2.0 (permissive) · 00c0672f3febbf9f · report
nv-tlabs/cosmos-drive-dreams community (archive-listed) 13 samples, 13 ran (0 instrument-failed) · 0 unverified
analyze_traffic_light_with_clip cosmos-drive-dreams-toolkits/crop_traffic_lights.py ran Apache-2.0 (permissive) · a64dcc826fd7beed · report fixture: signature image:Image/0/?, model:callable/0/?, transform:callable/0/?, class_names:list/1/str, device:str/0/str · returned str · level recorded 2026-09-24
calculate_metrics in 61 papers cosmos-drive-dreams-toolkits/train_light_model.py ran Apache-2.0 (permissive) · 55d080a2eba4d6b7 · report fixture: signature y_true:list/1/int, y_pred:list/1/int, class_names:list/1/str · returned dict · level recorded 2026-09-24
estimate_ground_height cosmos-drive-dreams-toolkits/visualize_rds_hq.py ran Apache-2.0 (permissive) · 7e236dc4ecb21240 · report fixture: signature front_camera_pose:ndarray/2/float, lane_lines:ndarray/3/float · returned float32 · level recorded 2026-09-25
extract_clip_id_from_image_name cosmos-drive-dreams-toolkits/crop_traffic_lights_for_training.py ran fingerprinted Apache-2.0 (permissive) · af33c328c499d24b · report fixture: signature image_name:str/0/str · returned str · level recorded 2026-09-24
get_nearest_lidar_indices cosmos-drive-dreams-toolkits/render_from_rds_hq.py ran fingerprinted Apache-2.0 (permissive) · 574a2f62de49c221 · report fixture: signature high_indices:list/1/int, step:int/0/int · returned tuple · level recorded 2026-09-24
get_rectification_image_grid cosmos-drive-dreams-toolkits/rectify_ftheta_to_pinhole.py ran Apache-2.0 (permissive) · 14680804773f0813 · report fixture: signature ftheta_camera_model:callable/0/?, pinhole_camera_model:callable/0/? · returned Tensor · level recorded 2026-09-24
grounding_pose cosmos-drive-dreams-toolkits/visualize_rds_hq.py ran Apache-2.0 (permissive) · 39b2df8191427550 · report fixture: signature input_pose:ndarray/2/float, reference_height:float/0/float, convention:str/0/str · returned ndarray · level recorded 2026-09-25
interpolate_pose cosmos-drive-dreams-toolkits/utils/bbox_utils.py ran Apache-2.0 (permissive) · 0bf9492cb31ff028 · report fixture: signature prev_pose:ndarray/2/float, next_pose:ndarray/2/float, t:float/0/float · returned ndarray · level recorded 2026-09-25
load_clip_model cosmos-drive-dreams-toolkits/crop_traffic_lights.py ran Apache-2.0 (permissive) · 2f19456eeaab8957 · report fixture: signature model_path:str/0/str, device:str/0/str · returned tuple · level recorded 2026-09-24
load_qwen_model cosmos-drive-dreams-toolkits/crop_traffic_lights.py ran fingerprinted Apache-2.0 (permissive) · 6e674ab7a391a0d2 · report fixture: signature device:str/0/str · returned tuple · level recorded 2026-09-25
quaternion_uniform_flip cosmos-drive-dreams-toolkits/utils/animation_utils.py ran Apache-2.0 (permissive) · 7e675e35b8ade959 · report fixture: signature q_list:list/1/Quaternion · returned list · level recorded 2026-09-24
simple_confusion_matrix cosmos-drive-dreams-toolkits/train_light_model.py ran Apache-2.0 (permissive) · 8381210aed1abe7f · report fixture: signature y_true:ndarray/1/int, y_pred:ndarray/1/int, num_classes:int/0/int · returned ndarray · level recorded 2026-09-24
simple_train_test_split cosmos-drive-dreams-toolkits/train_light_model.py ran Apache-2.0 (permissive) · c7633667302f3088 · report fixture: signature indices:list/1/int, labels:list/1/int, test_size:float/0/float, random_state:int/0/int · returned tuple · level recorded 2026-09-24

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections