Papers › AdaWorld: Learning Adaptable World Models with Latent Actions

AdaWorld: Learning Adaptable World Models with Latent Actions

24 Mar 2025arXiv:2503.18938archive 2025-07-28

Shenyuan Gao, Siyuan Zhou, Yilun Du, Jun Zhang, Chuang Gan

World models aim to learn action-controlled future prediction and have proven essential for the development of intelligent agents. However, most existing world models rely heavily on substantial action-labeled data and costly training, making it challenging to adapt to novel environments with heterogeneous actions through limited interactions. This limitation can hinder their applicability across broader domains. To overcome this limitation, we propose AdaWorld, an innovative world model learning approach that enables efficient adaptation. The key idea is to incorporate action information during the pretraining of world models. This is achieved by extracting latent actions from videos in a self-supervised manner, capturing the most critical transitions between frames. We then develop an autoregressive world model that conditions on these latent actions. This learning paradigm enables highly adaptable world models, facilitating efficient transfer and learning of new actions even with limited interactions and finetuning. Our comprehensive experiments across multiple environments demonstrate that AdaWorld achieves superior performance in both simulation quality and visual planning.

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 14 code samples harvested from 1 repository linked to this paper: 8 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 8 ran (4 with no instrument failure; 4 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 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

little-podi/adaworld officialmentioned in papermentioned on GitHubpytorchSyntology: 14 samples, 8 ran (4 instrument-failed) · 6 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

14 samples harvested: 8 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 6 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
1ran · violated contract
2ran · our draft was wrong
2ran; the contract check could not run
2ran
6unverified

Licence: 0 of the 14 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 little-podi/adaworld. “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.

little-podi/adaworld official repository 14 samples, 8 ran (4 instrument-failed) · 6 unverified
PositionalEncoding in 126 papers
census: 13 implementations from 9 papers, 9 distinct outputs across 5 buckets, one shared input per bucket
lam/lam/modules/lam.py ran Apache-2.0 (permissive) · 8c5678a9a3911e1b · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
RotaryEmbedding in 27 papers lam/lam/modules/lam.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 8ad0a69c31d2ece7 · report fixture: returned RotaryEmbedding · level recorded 2026-09-22
apply_rotary_emb in 121 papers lam/lam/modules/lam.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 2f3566324cb2f780 · report fixture: signature freqs:Tensor/1/float, t:Tensor/3/float, start_index:int/0/int, scale:float/0/float, seq_dim:int/0/int · returned Tensor · level recorded 2026-09-22
default in 430 papers lam/lam/modules/lam.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 846d368f28a9e305 · report fixture: signature val:Tensor/2/float, d:Tensor/2/float · returned Tensor · level recorded 2026-09-22
exists in 528 papers
census: 5 implementations from 103 papers, 1 distinct output on one shared input
lam/lam/modules/lam.py ran · violated contract Apache-2.0 (permissive) · 220f3bbcd151f23c · report fixture: signature val:NoneType/0/? · returned bool · level recorded 2026-09-22
patchify in 32 papers
census: 6 implementations from 8 papers, 6 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 2 of 3, arg 1: rank 5, kind float, dtype float32
lam/lam/modules/lam.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · 039179bb223e6c09 · report fixture: signature videos:Tensor/5/float, size:int/0/int · returned Tensor · level recorded 2026-09-22
rotate_half in 424 papers
census: 24 implementations from 96 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
lam/lam/modules/lam.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · a61b41823e31cfae · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
unpatchify in 18 papers lam/lam/modules/lam.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 141935b085e62f1f · report fixture: signature patches:Tensor/4/float, size:int/0/int, h_out:int/0/int, w_out:int/0/int · returned Tensor · level recorded 2026-09-22
LatentActionModel lam/lam/modules/lam.py unverified Apache-2.0 (permissive) · a2023a6877be4d73 · report
SelfAttention in 66 papers lam/lam/modules/lam.py unverified Apache-2.0 (permissive) · b1d5f5dfa4ddac49 · report
SpatioBlock lam/lam/modules/lam.py unverified Apache-2.0 (permissive) · b40b953448d6ee7a · report
SpatioTemporalBlock lam/lam/modules/lam.py unverified Apache-2.0 (permissive) · 738a3cb5f1d4148e · report
SpatioTemporalTransformer lam/lam/modules/lam.py unverified Apache-2.0 (permissive) · cc694583cfd5d77d · report
SpatioTransformer lam/lam/modules/lam.py unverified Apache-2.0 (permissive) · eff93e60a0b14d72 · 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 AdaWorld (graph method: AdaWorld). 14 bricks; individually on a fixture: 8 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

  1. LatentActionModel entry · level 0 · unverified · a2023a6877be4d73
  2. SpatioTemporalTransformer helper · level 0 · unverified · cc694583cfd5d77d
  3. SpatioTransformer helper · level 0 · unverified · eff93e60a0b14d72
  4. patchify helper · level 1 · ran; the contract check could not run (RAISES) · 039179bb223e6c09
  5. unpatchify helper · level 1 · ran; the contract check could not run (RAISES) · 141935b085e62f1f
  6. PositionalEncoding helper · level 1 · ran · 8c5678a9a3911e1b
  7. SpatioTemporalBlock helper · level 0 · unverified · 738a3cb5f1d4148e
  8. SpatioBlock helper · level 0 · unverified · b40b953448d6ee7a
  9. SelfAttention helper · level 0 · unverified · b1d5f5dfa4ddac49
  10. RotaryEmbedding helper · level 1 · ran · 8ad0a69c31d2ece7
  11. apply_rotary_emb helper · level 1 · ran · our draft was wrong · 2f3566324cb2f780
  12. default helper · level 1 · ran · honoured contract · 846d368f28a9e305
  13. exists helper · level 1 · ran · violated contract · 220f3bbcd151f23c
  14. rotate_half helper · level 1 · ran · our draft was wrong · a61b41823e31cfae

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="2503.18938") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Future prediction

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