Papers › Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability

Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability

27 May 2024arXiv:2405.17398archive 2025-07-28

Shenyuan Gao, Jiazhi Yang, Li Chen, Kashyap Chitta, Yihang Qiu, Andreas Geiger, Jun Zhang, Hongyang Li

World models can foresee the outcomes of different actions, which is of paramount importance for autonomous driving. Nevertheless, existing driving world models still have limitations in generalization to unseen environments, prediction fidelity of critical details, and action controllability for flexible application. In this paper, we present Vista, a generalizable driving world model with high fidelity and versatile controllability. Based on a systematic diagnosis of existing methods, we introduce several key ingredients to address these limitations. To accurately predict real-world dynamics at high resolution, we propose two novel losses to promote the learning of moving instances and structural information. We also devise an effective latent replacement approach to inject historical frames as priors for coherent long-horizon rollouts. For action controllability, we incorporate a versatile set of controls from high-level intentions (command, goal point) to low-level maneuvers (trajectory, angle, and speed) through an efficient learning strategy. After large-scale training, the capabilities of Vista can seamlessly generalize to different scenarios. Extensive experiments on multiple datasets show that Vista outperforms the most advanced general-purpose video generator in over 70% of comparisons and surpasses the best-performing driving world model by 55% in FID and 27% in FVD. Moreover, for the first time, we utilize the capacity of Vista itself to establish a generalizable reward for real-world action evaluation without accessing the ground truth actions.

PaperPDFCodeCode Syntology ranMethod as code

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 23 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 12 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 23 samples from 1 repository, 11 ran (6 with no instrument failure; 5 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

opendrivelab/vista officialmentioned in papermentioned on GitHubpytorchSyntology: 23 samples, 11 ran (5 instrument-failed) · 12 unverified report
opendrivelab/uniad mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Planning-oriented Autonomous Driving (arXiv:2212.10156; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

23 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 12 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.

1ran · honoured contract
5ran · our draft was wrong
5ran
12unverified

Licence: 0 of the 23 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 opendrivelab/vista. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

opendrivelab/vista official repository 23 samples, 11 ran (5 instrument-failed) · 12 unverified
AE3DConv vwm/models/diffusion.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · 5c64e7e669227c45 · report fixture: signature input:Tensor/4/float, timesteps:int/0/int, skip_video:bool/0/bool · returned Tensor · level recorded 2026-09-22
Conv2DWrapper vwm/models/diffusion.py ran fingerprinted Apache-2.0 (permissive) · 0c3b34cc52a71729 · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-24
LinAttnBlock vwm/models/diffusion.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 75aa8f65b96515b2 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
LinearAttention in 20 papers vwm/models/diffusion.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · b7508055b9e0c4d0 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
LitEma vwm/models/diffusion.py ran Apache-2.0 (permissive) · 1eefb4280050c186 · report fixture: signature model:callable/0/? · returned NoneType · level recorded 2026-09-24
Normalize in 154 papers vwm/models/diffusion.py ran · our draft was wrong Apache-2.0 (permissive) · 4c0a080d5b99b21b · report fixture: signature in_channels:int/0/int, num_groups:int/0/int · returned GroupNorm · level recorded 2026-09-22
default in 430 papers vwm/models/diffusion.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 80f84a2f0bef0561 · report fixture: signature val:int/0/int, d:int/0/int · returned int · level recorded 2026-09-22
disabled_train in 172 papers vwm/models/diffusion.py ran · our draft was wrong Apache-2.0 (permissive) · 694551f4a162c92a · report fixture: signature self:callable/0/?, mode:bool/0/bool · returned SimpleModel · level recorded 2026-09-22
get_obj_from_str in 52 papers vwm/models/diffusion.py ran · our draft was wrong Apache-2.0 (permissive) · 30d11b7b4428ab6e · report fixture: signature string:str/0/str, reload:bool/0/bool, invalidate_cache:bool/0/bool · returned type · level recorded 2026-09-22
instantiate_from_config in 47 papers vwm/models/diffusion.py ran · our draft was wrong Apache-2.0 (permissive) · f3ff5ab8d2f07e10 · report fixture: signature config:dict/0/? · returned Linear · level recorded 2026-09-22
partialclass in 13 papers vwm/models/diffusion.py ran · our draft was wrong Apache-2.0 (permissive) · c91c205a5fcd562b · report fixture: signature cls:callable/0/?, args:tuple/1/int, kwargs:dict/0/? · returned type · level recorded 2026-09-24
AttnBlock in 22 papers vwm/models/diffusion.py unverified Apache-2.0 (permissive) · 65943cc8c6a0822c · report
Decoder in 210 papers vwm/models/diffusion.py unverified Apache-2.0 (permissive) · 77628e616403b945 · report
DiffusionEngine vwm/models/diffusion.py unverified Apache-2.0 (permissive) · 0827884f986ea385 · report
MemoryEfficientAttnBlock vwm/models/diffusion.py unverified Apache-2.0 (permissive) · 335d93824445f73a · report
MemoryEfficientCrossAttention in 7 papers vwm/models/diffusion.py unverified Apache-2.0 (permissive) · 9a1320c38ff3a00b · report
MemoryEfficientCrossAttentionWrapper vwm/models/diffusion.py unverified Apache-2.0 (permissive) · 7eeaf0d0942c8b14 · report
ResnetBlock in 49 papers vwm/models/diffusion.py unverified Apache-2.0 (permissive) · 3aba0be80d3762a9 · report
TimestepBlock in 11 papers vwm/models/diffusion.py unverified Apache-2.0 (permissive) · 3996f5eb1a63c585 · report
VideoDecoder vwm/models/diffusion.py unverified Apache-2.0 (permissive) · 634ba52fa75838b3 · report
VideoResBlock vwm/models/diffusion.py unverified Apache-2.0 (permissive) · d865fe90a754a2c9 · report
make_attn in 22 papers vwm/models/diffusion.py unverified Apache-2.0 (permissive) · df7cb18ec3f78d30 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Vista (graph method: Vista). 28 bricks; individually on a fixture: 16 ran (of which 2 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 1 violated, 7 with no contract checked; 7 where Syntology's instrument failed) · 12 unverified. The assembly has not been run end-to-end.

  1. DiffusionEngine entry · level 0 · unverified · 0827884f986ea385
  2. LitEma helper · level 1 · ran · 1eefb4280050c186
  3. VideoDecoder helper · level 0 · unverified · 634ba52fa75838b3
  4. default helper · level 1 · ran · honoured contract · 80f84a2f0bef0561
  5. disabled_train helper · level 1 · ran · our draft was wrong · 694551f4a162c92a
  6. get_obj_from_str helper · level 1 · ran · our draft was wrong · 30d11b7b4428ab6e
  7. instantiate_from_config helper · level 1 · ran · our draft was wrong · f3ff5ab8d2f07e10
  8. AE3DConv helper · level 1 · ran · 5c64e7e669227c45
  9. Conv2DWrapper helper · level 1 · ran · 0c3b34cc52a71729
  10. Decoder model · level 0 · unverified · 77628e616403b945
  11. VideoResBlock helper · level 0 · unverified · d865fe90a754a2c9
  12. partialclass helper · level 1 · ran · our draft was wrong · c91c205a5fcd562b
  13. exists helper · level 1 · ran · violated contract · 608e364a9d2376a3
  14. Normalize helper · level 1 · ran · our draft was wrong · 4c0a080d5b99b21b
  15. ResnetBlock helper · level 0 · unverified · 3aba0be80d3762a9
  16. Upsample helper · level 1 · ran · aa5c10aa30eb8173
  17. make_attn helper · level 0 · unverified · df7cb18ec3f78d30
  18. nonlinearity helper · level 1 · ran · our draft was wrong · 3137073275f8c21a
  19. ResBlock helper · level 0 · unverified · 30af670fe741ec02
  20. AttnBlock helper · level 0 · unverified · 65943cc8c6a0822c
  21. LinAttnBlock helper · level 1 · ran · 75aa8f65b96515b2
  22. MemoryEfficientAttnBlock helper · level 0 · unverified · 335d93824445f73a
  23. MemoryEfficientCrossAttentionWrapper helper · level 0 · unverified · 7eeaf0d0942c8b14
  24. Downsample helper · level 1 · ran · 6618daf64230cf0c
  25. TimestepBlock helper · level 0 · unverified · 3996f5eb1a63c585
  26. zero_module helper · level 1 · ran · our draft was wrong · 129b804760b3115f
  27. LinearAttention helper · level 1 · ran · b7508055b9e0c4d0
  28. MemoryEfficientCrossAttention helper · level 0 · unverified · 9a1320c38ff3a00b

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2405.17398") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Autonomous DrivingVideo Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SET

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