Papers › Latent Action Pretraining from Videos
Latent Action Pretraining from Videos
Seonghyeon Ye, Joel Jang, Byeongguk Jeon, Sejune Joo, Jianwei Yang, Baolin Peng, Ajay Mandlekar, Reuben Tan, Yu-Wei Chao, Bill Yuchen Lin, Lars Liden, Kimin Lee, Jianfeng Gao, Luke Zettlemoyer, Dieter Fox, Minjoon Seo
We introduce Latent Action Pretraining for general Action models (LAPA), an unsupervised method for pretraining Vision-Language-Action (VLA) models without ground-truth robot action labels. Existing Vision-Language-Action models require action labels typically collected by human teleoperators during pretraining, which significantly limits possible data sources and scale. In this work, we propose a method to learn from internet-scale videos that do not have robot action labels. We first train an action quantization model leveraging VQ-VAE-based objective to learn discrete latent actions between image frames, then pretrain a latent VLA model to predict these latent actions from observations and task descriptions, and finally finetune the VLA on small-scale robot manipulation data to map from latent to robot actions. Experimental results demonstrate that our method significantly outperforms existing techniques that train robot manipulation policies from large-scale videos. Furthermore, it outperforms the state-of-the-art VLA model trained with robotic action labels on real-world manipulation tasks that require language conditioning, generalization to unseen objects, and semantic generalization to unseen instructions. Training only on human manipulation videos also shows positive transfer, opening up the potential for leveraging web-scale data for robotics foundation model.
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):
get_harvested_code_for_paper(arxiv_id="2410.11758")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2410.11758", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2410.11758")
Code
Syntology 36 code samples harvested from 3 repositories linked to this paper: 30 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 4 honoured, 5 violated, 9 with no contract checked; 12 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 9 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: community (archive-listed): 14 samples from 1 repository, 12 ran (10 with no instrument failure; 2 where Syntology's instrument failed); found in paper text by Syntology: 22 samples from 2 repositories, 18 ran (8 with no instrument failure; 10 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. 3 of the 30 samples that ran have no recorded date.
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
36 samples harvested: 30 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 4 honoured, 5 violated, 9 with no contract checked; 12 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 4 of the 36 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from 3 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. 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.
census: 11 implementations from 39 papers, 3 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32 laq/laq_model/data.py ran · honoured contract MIT (permissive) ·
7f1040f5e3991d5e · report
fixture: signature t:Tensor/2/float, args:tuple/1/Tensor, kwargs:dict/0/? · returned Tensor · level recorded, date not recorded 5d19651094278e5c · report
fixture: signature log:dict/0/?, new_logs:dict/0/? · returned dict · level recorded 2026-09-24 60fff7c3c400d7ff · report
fixture: signature val:int/0/int, d:int/0/int · returned int · level recorded, date not recorded 9056e6d6fdefa088 · report
fixture: signature vqgan:MockVQGAN/0/?, images:ArrayImpl/4/float · returned ndarray · level recorded 2026-09-24 census: 5 implementations from 103 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64 laq/laq_model/attention.py ran · violated contract MIT (permissive) here; the stored copy is pointer only ·
aa5486a3650902d8 · report
fixture: signature val:Tensor/1/int · returned bool · level recorded, date not recorded 93576b1f69752368 · report
fixture: signature params:list/1/Tensor, lr:float/0/float, wd:float/0/float, betas:tuple/1/float, eps:float/0/float, filter_by_requires_grad:bool/0/bool, group_wd_params:bool/0/bool · returned AdamW · level recorded 2026-09-24 bf465416561b7be4 · report
fixture: signature image_aug:bool/0/bool · returned Compose · level recorded 2026-09-24 f11bef5e87ce3904 · report
fixture: signature p:float/0/float · returned LeakyReLU · level recorded 2026-09-22 0ca8f8ec94f51579 · report
fixture: returned tuple · level recorded 2026-09-24 6d5ab71931a90677 · report
fixture: signature val:int/0/int · returned tuple · level recorded 2026-09-22 9270ed2833cf3467 · report
fixture: signature val:int/0/int · returned tuple · level recorded 2026-09-24 fdc11aefc97f3abb · report
fixture: signature params:list/1/Tensor · returned tuple · level recorded 2026-09-24 cbdf413e88112af9 · report
dbc74cddc2c0fb0a · report
fixture: signature image:ndarray/3/int, info_dict:dict/0/?, pos:tuple/1/int, font:int/0/int, font_scale:int/0/int, font_thickness:int/0/int, text_color:tuple/1/int · returned ndarray · level recorded 2026-09-24 155c970270f7efea · report
fixture: signature images:EagerTensor/4/float, random_crop_factor:float/0/float · returned EagerTensor · level recorded 2026-09-24 0eb50fb69cca4ed3 · report
fixture: signature fn:callable/0/? · returned function · level recorded 2026-09-24 9c310e911f805732 · report
fixture: signature h:MockHyperparameter/0/? · returned list · level recorded 2026-09-24 0b15aed1f08da820 · report
fixture: signature images:ArrayImpl/4/float · returned ArrayImpl · level recorded 2026-09-24 c212071abd4e5321 · report
fixture: signature d_model:int/0/int, height:int/0/int, width:int/0/int, flatten:bool/0/bool · returned ndarray · level recorded 2026-09-24 98869bb596d5d642 · report
fixture: signature images:EagerTensor/4/float, target_height:int/0/int, target_width:int/0/int · returned EagerTensor · level recorded 2026-09-24 02dbbb5108872c5d · report
fixture: signature max_len:int/0/int, max_timescale:float/0/float · returned function · level recorded 2026-09-24 cbf0a809513fd118 · report
c30c34bf7965a040 · report
86c900797b149647 · report
f38cfe2cf5433ba8 · report
2291e98cc51d78b6 · report
fixture: signature n_trials_per_ckpt:int/0/int, success:list/1/float · returned ndarray · level recorded 2026-09-24 b473600d9d00e657 · report
fixture: signature dataset_name:str/0/str · returned str · level recorded 2026-09-24 3abdec7a01649789 · report
fixture: signature obj:ndarray/2/float · returned dict · level recorded 2026-09-24 1d86046b8135d67a · report
fixture: signature path:str/0/str · returned bool · level recorded 2026-09-24 2b562af5f9efa42f · report
fixture: signature image_paths:ndarray/3/int · returned tuple · level recorded 2026-09-24 1a0db059d2e3b91b · report
fixture: signature image_paths:str/0/str · returned tuple · level recorded 2026-09-24 441fe6ea8aeea865 · report
fixture: signature perf_sim:list/1/float, perf_real:list/1/float · returned float64 · level recorded 2026-09-24 8cd74b85e5838b36 · report
fixture: signature dct:dict/0/? · returned ndarray · level recorded 2026-09-24 05c86bc7ce4ad9dc · report
fixture: signature t:tuple/1/float · returned ndarray · level recorded 2026-09-24 9dbd294d9713950c · report
fixture: signature perf_sim:list/1/float, perf_real:list/1/float · returned int · level recorded 2026-09-24 Tasks
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